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

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

Neuron 2132 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1510218 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2511. Min Act: -0.0000

Data Index: 138927 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2542. Min Act: -0.0000

Data Index: 132456 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1595840 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2390. Min Act: -0.0000

Data Index: 806880 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2304. Min Act: -0.0000

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1416447 (Python Code)

Max Activating Token Index: 695

Text #8

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2357. Min Act: -0.0000

Data Index: 562873 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1442803 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2176. Min Act: -0.0000

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2233. Min Act: -0.0000

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2221. Min Act: -0.0000

Data Index: 283753 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2187. Min Act: -0.0000

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2196. Min Act: -0.0000

Data Index: 116894 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1596416 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2161. Min Act: -0.0000

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1195087 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1214729 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2122. Min Act: -0.0000

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 64