< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 60 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0003

Data Index: 1402891 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1493. Min Act: -0.0003

Data Index: 1849286 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1450. Min Act: -0.0003

Data Index: 1380535 (The Pile)

Max Activating Token Index: 395

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1294. Min Act: -0.0003

Data Index: 117591 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1285. Min Act: -0.0003

Data Index: 457150 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1250. Min Act: -0.0003

Data Index: 1647442 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1136. Min Act: -0.0003

Data Index: 83248 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1201. Min Act: -0.0003

Data Index: 669052 (The Pile)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1147. Min Act: -0.0002

Data Index: 743450 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0912. Min Act: -0.0003

Data Index: 1698370 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1053. Min Act: -0.0003

Data Index: 1795689 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1075. Min Act: -0.0003

Data Index: 1515263 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1033. Min Act: -0.0003

Data Index: 528186 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0889. Min Act: -0.0003

Data Index: 115943 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1267936 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1022. Min Act: -0.0003

Data Index: 1682187 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1105008 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0880. Min Act: -0.0003

Data Index: 370105 (The Pile)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0758. Min Act: -0.0003

Data Index: 152807 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.0701. Min Act: -0.0003

Data Index: 841220 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #19