< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4072 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1961653 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3932. Min Act: -0.0001

Data Index: 141094 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3919. Min Act: -0.0001

Data Index: 203426 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3457. Min Act: -0.0001

Data Index: 605082 (The Pile)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3530. Min Act: -0.0001

Data Index: 183237 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1433882 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3479. Min Act: -0.0001

Data Index: 1668680 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3605. Min Act: -0.0001

Data Index: 800279 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3603. Min Act: -0.0001

Data Index: 994977 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3256. Min Act: -0.0001

Data Index: 1538450 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1370344 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3426. Min Act: -0.0001

Data Index: 1543447 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1128348 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1634299 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3474. Min Act: -0.0001

Data Index: 12055 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3346. Min Act: -0.0001

Data Index: 1427398 (The Pile)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3284. Min Act: -0.0001

Data Index: 252891 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3411. Min Act: -0.0001

Data Index: 809393 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3287. Min Act: -0.0001

Data Index: 572296 (The Pile)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1546352 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #19