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

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

Neuron 3419 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7330. Min Range: -5.7330

Max Act: 5.7330. Min Act: -0.0001

Data Index: 435269 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 5.7330. Min Range: -5.7330

Max Act: 5.7270. Min Act: -0.0001

Data Index: 884780 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 5.7330. Min Range: -5.7330

Max Act: 5.3331. Min Act: -0.0001

Data Index: 1199022 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 5.7330. Min Range: -5.7330

Max Act: 5.1278. Min Act: -0.0001

Data Index: 1101911 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.8381. Min Act: -0.0001

Data Index: 1354109 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 5.7330. Min Range: -5.7330

Max Act: 5.5058. Min Act: -0.0001

Data Index: 250698 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 5.7330. Min Range: -5.7330

Max Act: 5.0669. Min Act: -0.0001

Data Index: 1113587 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.6161. Min Act: -0.0001

Data Index: 1224208 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.7117. Min Act: -0.0001

Data Index: 854439 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.8875. Min Act: -0.0001

Data Index: 107207 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 5.7330. Min Range: -5.7330

Max Act: 5.2147. Min Act: -0.0001

Data Index: 627191 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.3197. Min Act: -0.0001

Data Index: 176260 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.4321. Min Act: -0.0001

Data Index: 857366 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.1720. Min Act: -0.0001

Data Index: 514346 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.6348. Min Act: -0.0001

Data Index: 238980 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.6668. Min Act: -0.0001

Data Index: 842191 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.8528. Min Act: -0.0001

Data Index: 318825 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.2812. Min Act: -0.0001

Data Index: 495273 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.5572. Min Act: -0.0001

Data Index: 1028937 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 5.7330. Min Range: -5.7330

Max Act: 4.0446. Min Act: -0.0001

Data Index: 147225 (C4 (Web Text))

Max Activating Token Index: 815