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

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

Neuron 3005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1417552 (Python Code)

Max Activating Token Index: 504

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1149017 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0164. Min Act: -0.0002

Data Index: 53678 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1612441 (Python Code)

Max Activating Token Index: 159

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0163. Min Act: -0.0002

Data Index: 826713 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0164. Min Act: -0.0002

Data Index: 545719 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1394834 (Python Code)

Max Activating Token Index: 542

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0159. Min Act: -0.0002

Data Index: 908932 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0159. Min Act: -0.0002

Data Index: 222720 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1301410 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1529070 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1636911 (Python Code)

Max Activating Token Index: 415

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0157. Min Act: -0.0002

Data Index: 766353 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0157. Min Act: -0.0002

Data Index: 317012 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1596373 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1391108 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1207022 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1481150 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0146. Min Act: -0.0002

Data Index: 92592 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1580064 (Python Code)

Max Activating Token Index: 161