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

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

Neuron 2504 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0283. Min Act: -0.0003

Data Index: 568374 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0198. Min Act: -0.0003

Data Index: 109406 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0184. Min Act: -0.0003

Data Index: 282356 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1605062 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0181. Min Act: -0.0003

Data Index: 91534 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0179. Min Act: -0.0003

Data Index: 18027 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1136841 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0175. Min Act: -0.0003

Data Index: 537703 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1162043 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0175. Min Act: -0.0003

Data Index: 107724 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0174. Min Act: -0.0003

Data Index: 247534 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1583269 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1258128 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0173. Min Act: -0.0003

Data Index: 615970 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0169. Min Act: -0.0002

Data Index: 646815 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0171. Min Act: -0.0003

Data Index: 904821 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1223928 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0167. Min Act: -0.0003

Data Index: 256796 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1468975 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0164. Min Act: -0.0003

Data Index: 918471 (C4 (Web Text))

Max Activating Token Index: 465