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

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

Neuron 328 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: 0.7301. Min Range: -0.7301

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1356852 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1365898 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1328850 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1609950 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5198. Min Act: -0.0000

Data Index: 432562 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4971. Min Act: -0.0000

Data Index: 819459 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4986. Min Act: -0.0000

Data Index: 473097 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4653. Min Act: -0.0000

Data Index: 794450 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4480. Min Act: -0.0000

Data Index: 972316 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1032368 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4693. Min Act: -0.0000

Data Index: 59292 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4546. Min Act: -0.0000

Data Index: 259959 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1116821 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1602307 (Python Code)

Max Activating Token Index: 441

Text #14

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1595798 (Python Code)

Max Activating Token Index: 730

Text #15

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4149. Min Act: -0.0000

Data Index: 434390 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4239. Min Act: -0.0000

Data Index: 995989 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4415. Min Act: -0.0000

Data Index: 743502 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4390. Min Act: -0.0000

Data Index: 871478 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.7301. Min Range: -0.7301

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1010841 (C4 (Web Text))

Max Activating Token Index: 727