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

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

Neuron 1203 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0179. Min Act: -0.0003

Data Index: 589300 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1286519 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0172. Min Act: -0.0003

Data Index: 535732 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1266063 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0168. Min Act: -0.0003

Data Index: 316102 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1071145 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1247343 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1622860 (Python Code)

Max Activating Token Index: 505

Text #8

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1054207 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1186272 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0159. Min Act: -0.0002

Data Index: 805836 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1639921 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1503795 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0157. Min Act: -0.0003

Data Index: 178905 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0156. Min Act: -0.0003

Data Index: 332799 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1275340 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0149. Min Act: -0.0003

Data Index: 360838 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0152. Min Act: -0.0003

Data Index: 409219 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1429677 (Python Code)

Max Activating Token Index: 636

Text #19

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0155. Min Act: -0.0003

Data Index: 596400 (C4 (Web Text))

Max Activating Token Index: 829