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

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

Neuron 4725 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0002

Data Index: 348373 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1352864 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0182. Min Act: -0.0002

Data Index: 106357 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1540128 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0176. Min Act: -0.0002

Data Index: 248014 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1082305 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1367005 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0170. Min Act: -0.0002

Data Index: 834764 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0172. Min Act: -0.0002

Data Index: 846285 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0168. Min Act: -0.0002

Data Index: 509958 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0167. Min Act: -0.0002

Data Index: 130348 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1377206 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1580886 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0165. Min Act: -0.0002

Data Index: 245460 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1379271 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1578046 (Python Code)

Max Activating Token Index: 172

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0161. Min Act: -0.0002

Data Index: 275438 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1474713 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0161. Min Act: -0.0002

Data Index: 53276 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1303760 (C4 (Web Text))

Max Activating Token Index: 75