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

Dataset: The Pile

Neuron 363 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.4226. Min Act: -0.0000

Data Index: 995339 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1495789 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1943029 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3487. Min Act: -0.0000

Data Index: 240000 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1277125 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1913899 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3245. Min Act: -0.0000

Data Index: 39164 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1975617 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1387596 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2606. Min Act: -0.0000

Data Index: 271199 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1209170 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2505. Min Act: -0.0000

Data Index: 136838 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1779835 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1165678 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2483. Min Act: -0.0000

Data Index: 45488 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2459. Min Act: -0.0000

Data Index: 74927 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2117. Min Act: -0.0000

Data Index: 403944 (The Pile)

Max Activating Token Index: 942

Text #17

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1323979 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2413. Min Act: -0.0000

Data Index: 278692 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1667534 (The Pile)

Max Activating Token Index: 316