Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1294 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.4306. Min Act: -0.0004

Data Index: 1331492 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.4305. Min Act: -0.0003

Data Index: 517392 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3465. Min Act: -0.0003

Data Index: 760740 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3190. Min Act: -0.0003

Data Index: 882187 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3787. Min Act: -0.0003

Data Index: 664557 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3219. Min Act: -0.0004

Data Index: 407552 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3467. Min Act: -0.0003

Data Index: 872933 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3687. Min Act: -0.0003

Data Index: 627625 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3392. Min Act: -0.0003

Data Index: 574068 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3130. Min Act: -0.0003

Data Index: 898764 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3321. Min Act: -0.0003

Data Index: 374526 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3452. Min Act: -0.0004

Data Index: 254828 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3135. Min Act: -0.0004

Data Index: 848194 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3221. Min Act: -0.0003

Data Index: 1155586 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3231. Min Act: -0.0003

Data Index: 1204289 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3094. Min Act: -0.0004

Data Index: 1112765 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3292. Min Act: -0.0004

Data Index: 38825 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3207. Min Act: -0.0003

Data Index: 1104930 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.3330. Min Act: -0.0003

Data Index: 410164 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.4306. Min Range: -0.4306

Max Act: 0.2956. Min Act: -0.0003

Data Index: 110207 (C4 (Web Text))

Max Activating Token Index: 789