Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3858 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1299463 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.4205. Min Act: -0.0000

Data Index: 75789 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.3717. Min Act: -0.0000

Data Index: 855037 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.4769. Min Act: -0.0000

Data Index: 24525 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.2612. Min Act: -0.0000

Data Index: 16278 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.3326. Min Act: -0.0000

Data Index: 609537 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.3526. Min Act: -0.0000

Data Index: 916769 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.3157. Min Act: -0.0000

Data Index: 390370 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.3292. Min Act: -0.0000

Data Index: 264145 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.2984. Min Act: -0.0000

Data Index: 571438 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.2478. Min Act: -0.0000

Data Index: 459919 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.3217. Min Act: -0.0000

Data Index: 226658 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1293827 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.1216. Min Act: -0.0000

Data Index: 539422 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1298670 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.2638. Min Act: -0.0000

Data Index: 743812 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.1501. Min Act: -0.0000

Data Index: 483085 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.2604. Min Act: -0.0000

Data Index: 1298962 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.1803. Min Act: -0.0000

Data Index: 850056 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 1.5167. Min Range: -1.5167

Max Act: 1.2863. Min Act: -0.0000

Data Index: 322824 (C4 (Web Text))

Max Activating Token Index: 632