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

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

Neuron 3632 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0197. Min Act: -0.0002

Data Index: 149720 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0203. Min Act: -0.0002

Data Index: 249196 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0169. Min Act: -0.0002

Data Index: 102140 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1197981 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0158. Min Act: -0.0002

Data Index: 105215 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1129145 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0162. Min Act: -0.0002

Data Index: 339444 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0152. Min Act: -0.0002

Data Index: 476543 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1558788 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0157. Min Act: -0.0002

Data Index: 882478 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0156. Min Act: -0.0002

Data Index: 338878 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0157. Min Act: -0.0002

Data Index: 553764 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1155928 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0140. Min Act: -0.0002

Data Index: 589445 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0160. Min Act: -0.0002

Data Index: 709873 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0143. Min Act: -0.0002

Data Index: 458380 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0161. Min Act: -0.0002

Data Index: 925551 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0149. Min Act: -0.0002

Data Index: 747807 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1122285 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1473027 (Python Code)

Max Activating Token Index: 362