Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 199 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0003

Data Index: 230498 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0403. Min Act: -0.0004

Data Index: 357064 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1316058 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1006179 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0392. Min Act: -0.0004

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0378. Min Act: -0.0004

Data Index: 1199961 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0370. Min Act: -0.0003

Data Index: 533581 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1336506 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1271994 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0359. Min Act: -0.0004

Data Index: 1062353 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0376. Min Act: -0.0003

Data Index: 532960 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0376. Min Act: -0.0003

Data Index: 160259 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1030954 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0359. Min Act: -0.0003

Data Index: 440129 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0356. Min Act: -0.0003

Data Index: 149524 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0355. Min Act: -0.0003

Data Index: 393371 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1306386 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0353. Min Act: -0.0003

Data Index: 467325 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0356. Min Act: -0.0003

Data Index: 239968 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0354. Min Act: -0.0003

Data Index: 966116 (C4 (Web Text))

Max Activating Token Index: 165