< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3071 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3450. Min Act: -0.0002

Data Index: 1513877 (The Pile)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3317. Min Act: -0.0002

Data Index: 896395 (The Pile)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3126. Min Act: -0.0002

Data Index: 138838 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3186. Min Act: -0.0002

Data Index: 1738592 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2941. Min Act: -0.0002

Data Index: 1970082 (The Pile)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2952. Min Act: -0.0002

Data Index: 1259241 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.3015. Min Act: -0.0002

Data Index: 947319 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2953. Min Act: -0.0002

Data Index: 917970 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2941. Min Act: -0.0002

Data Index: 285063 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2856. Min Act: -0.0002

Data Index: 383386 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2921. Min Act: -0.0002

Data Index: 1301739 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2894. Min Act: -0.0002

Data Index: 227550 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2890. Min Act: -0.0002

Data Index: 836649 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2886. Min Act: -0.0002

Data Index: 1652408 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2742. Min Act: -0.0002

Data Index: 488210 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2760. Min Act: -0.0002

Data Index: 456190 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2845. Min Act: -0.0002

Data Index: 84587 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2925. Min Act: -0.0002

Data Index: 1058731 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2707. Min Act: -0.0002

Data Index: 1465084 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3450. Min Range: -0.3450

Max Act: 0.2801. Min Act: -0.0002

Data Index: 488432 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #19