Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 93 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.6777. Min Act: -0.0001

Data Index: 100874 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.2448. Min Act: -0.0001

Data Index: 581716 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.2088. Min Act: -0.0001

Data Index: 1067808 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.2549. Min Act: -0.0001

Data Index: 1067239 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.2032. Min Act: -0.0001

Data Index: 308895 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.2652. Min Act: -0.0001

Data Index: 908409 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.4012. Min Act: -0.0001

Data Index: 348517 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.1222. Min Act: -0.0001

Data Index: 900969 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.1039. Min Act: -0.0001

Data Index: 295666 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.2354. Min Act: -0.0001

Data Index: 734108 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 3.6777. Min Range: -3.6777

Max Act: 3.2401. Min Act: -0.0001

Data Index: 900679 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.9253. Min Act: -0.0001

Data Index: 1282591 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.8743. Min Act: -0.0001

Data Index: 1096364 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.7162. Min Act: -0.0001

Data Index: 1039678 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.9454. Min Act: -0.0001

Data Index: 233317 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.6314. Min Act: -0.0001

Data Index: 1344596 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.4771. Min Act: -0.0001

Data Index: 58820 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.4553. Min Act: -0.0001

Data Index: 40973 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.5538. Min Act: -0.0001

Data Index: 1139365 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 3.6777. Min Range: -3.6777

Max Act: 2.5235. Min Act: -0.0001

Data Index: 338220 (C4 (Web Text))

Max Activating Token Index: 390