Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1556 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1183812 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0312. Min Act: -0.0005

Data Index: 11919 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0306. Min Act: -0.0005

Data Index: 994213 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0282. Min Act: -0.0005

Data Index: 510788 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0280. Min Act: -0.0005

Data Index: 1616794 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0284. Min Act: -0.0005

Data Index: 123279 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0281. Min Act: -0.0005

Data Index: 478024 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1148905 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0272. Min Act: -0.0005

Data Index: 379288 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0274. Min Act: -0.0005

Data Index: 18088 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0274. Min Act: -0.0005

Data Index: 227069 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0261. Min Act: -0.0005

Data Index: 462887 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0260. Min Act: -0.0005

Data Index: 931662 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0257. Min Act: -0.0005

Data Index: 874912 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0252. Min Act: -0.0005

Data Index: 483053 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1411467 (Python Code)

Max Activating Token Index: 548

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0251. Min Act: -0.0005

Data Index: 220707 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0256. Min Act: -0.0005

Data Index: 617176 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0254. Min Act: -0.0005

Data Index: 960102 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1429627 (Python Code)

Max Activating Token Index: 332