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

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

Neuron 2732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8971. Min Range: -7.8971

Max Act: 7.8971. Min Act: -0.0000

Data Index: 1011688 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 7.8971. Min Range: -7.8971

Max Act: 7.2691. Min Act: -0.0000

Data Index: 1114417 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.9646. Min Act: -0.0000

Data Index: 908409 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.9557. Min Act: -0.0000

Data Index: 581716 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 7.8971. Min Range: -7.8971

Max Act: 7.1344. Min Act: -0.0000

Data Index: 295666 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.9175. Min Act: -0.0000

Data Index: 514827 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 7.8971. Min Range: -7.8971

Max Act: 7.1002. Min Act: -0.0000

Data Index: 1039732 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.9552. Min Act: -0.0000

Data Index: 1067239 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.5479. Min Act: -0.0000

Data Index: 901700 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 7.8971. Min Range: -7.8971

Max Act: 7.0854. Min Act: -0.0000

Data Index: 348517 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.3275. Min Act: -0.0000

Data Index: 68095 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.5914. Min Act: -0.0000

Data Index: 23928 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.1149. Min Act: -0.0000

Data Index: 620974 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.0382. Min Act: -0.0000

Data Index: 262376 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 7.8971. Min Range: -7.8971

Max Act: 5.7467. Min Act: -0.0000

Data Index: 1003155 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 7.8971. Min Range: -7.8971

Max Act: 5.9212. Min Act: -0.0000

Data Index: 1340451 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.0234. Min Act: -0.0000

Data Index: 1329562 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 7.8971. Min Range: -7.8971

Max Act: 5.8397. Min Act: -0.0000

Data Index: 948585 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 7.8971. Min Range: -7.8971

Max Act: 6.0117. Min Act: -0.0000

Data Index: 150565 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 7.8971. Min Range: -7.8971

Max Act: 5.6264. Min Act: -0.0000

Data Index: 244845 (C4 (Web Text))

Max Activating Token Index: 769