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

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

Neuron 999 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: 2.4204. Min Range: -2.4204

Max Act: 2.4204. Min Act: -0.0000

Data Index: 444089 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 2.4204. Min Range: -2.4204

Max Act: 2.2978. Min Act: -0.0000

Data Index: 526033 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 2.4204. Min Range: -2.4204

Max Act: 2.1227. Min Act: -0.0000

Data Index: 276660 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 2.4204. Min Range: -2.4204

Max Act: 2.1189. Min Act: -0.0000

Data Index: 288297 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 2.4204. Min Range: -2.4204

Max Act: 2.1220. Min Act: -0.0000

Data Index: 601468 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 2.4204. Min Range: -2.4204

Max Act: 2.0954. Min Act: -0.0000

Data Index: 769698 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 2.4204. Min Range: -2.4204

Max Act: 2.0669. Min Act: -0.0000

Data Index: 1273543 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.9331. Min Act: -0.0000

Data Index: 466818 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.8228. Min Act: -0.0000

Data Index: 1033640 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.8975. Min Act: -0.0000

Data Index: 96115 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1188585 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 2.4204. Min Range: -2.4204

Max Act: 2.0780. Min Act: -0.0000

Data Index: 1171941 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.7804. Min Act: -0.0000

Data Index: 71853 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.8435. Min Act: -0.0000

Data Index: 80372 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.6344. Min Act: -0.0000

Data Index: 624524 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.6110. Min Act: -0.0000

Data Index: 15307 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1330549 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.7892. Min Act: -0.0000

Data Index: 1168361 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.7769. Min Act: -0.0000

Data Index: 599136 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.4204. Min Range: -2.4204

Max Act: 1.5517. Min Act: -0.0000

Data Index: 713877 (C4 (Web Text))

Max Activating Token Index: 215