Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2096 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0353. Min Act: -0.0003

Data Index: 172468 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0335. Min Act: -0.0003

Data Index: 595670 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0003

Data Index: 588926 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1211204 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0321. Min Act: -0.0003

Data Index: 329944 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1046412 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0332. Min Act: -0.0003

Data Index: 457689 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0333. Min Act: -0.0003

Data Index: 176326 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1140232 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0272. Min Act: -0.0003

Data Index: 159307 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0312. Min Act: -0.0003

Data Index: 363055 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1069999 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0309. Min Act: -0.0003

Data Index: 571647 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1029843 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1323094 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0307. Min Act: -0.0003

Data Index: 570788 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1190476 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0315. Min Act: -0.0003

Data Index: 755881 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0298. Min Act: -0.0003

Data Index: 380006 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0301. Min Act: -0.0003

Data Index: 385146 (C4 (Web Text))

Max Activating Token Index: 38