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

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

Neuron 1290 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3160. Min Act: -0.0000

Data Index: 835204 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2784. Min Act: -0.0000

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1040668 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2466. Min Act: -0.0001

Data Index: 417721 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2517. Min Act: -0.0000

Data Index: 861578 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2392. Min Act: -0.0000

Data Index: 448567 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2204. Min Act: -0.0000

Data Index: 140727 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1152317 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2355. Min Act: -0.0000

Data Index: 46060 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2255. Min Act: -0.0001

Data Index: 579186 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2184. Min Act: -0.0000

Data Index: 959947 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1336705 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2102. Min Act: -0.0000

Data Index: 145212 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2238. Min Act: -0.0000

Data Index: 718470 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2152. Min Act: -0.0000

Data Index: 756640 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2102. Min Act: -0.0000

Data Index: 234045 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1342755 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2130. Min Act: -0.0000

Data Index: 87786 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1038350 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1362159 (Python Code)

Max Activating Token Index: 310