< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 40 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0001

Data Index: 98157 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1259524 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0301. Min Act: -0.0001

Data Index: 887318 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0283. Min Act: -0.0001

Data Index: 601375 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0298. Min Act: -0.0001

Data Index: 776681 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0277. Min Act: -0.0001

Data Index: 919647 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1004619 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1972803 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1339209 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1911449 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0287. Min Act: -0.0001

Data Index: 806982 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1338987 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0297. Min Act: -0.0001

Data Index: 400133 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0282. Min Act: -0.0001

Data Index: 271465 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0282. Min Act: -0.0001

Data Index: 598212 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0273. Min Act: -0.0001

Data Index: 439074 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1619694 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1303834 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0272. Min Act: -0.0001

Data Index: 949117 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1651072 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #19