Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1915 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0174. Min Act: -0.0001

Data Index: 543757 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1242625 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0175. Min Act: -0.0002

Data Index: 524156 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0171. Min Act: -0.0001

Data Index: 616964 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1185252 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1009567 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0151. Min Act: -0.0001

Data Index: 1151450 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0155. Min Act: -0.0001

Data Index: 1259128 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0162. Min Act: -0.0002

Data Index: 111587 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0168. Min Act: -0.0001

Data Index: 370310 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0156. Min Act: -0.0001

Data Index: 225778 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0144. Min Act: -0.0001

Data Index: 762224 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1075088 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0152. Min Act: -0.0001

Data Index: 1157891 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0146. Min Act: -0.0001

Data Index: 775732 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0157. Min Act: -0.0001

Data Index: 739124 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0152. Min Act: -0.0001

Data Index: 200318 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0151. Min Act: -0.0001

Data Index: 904168 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0143. Min Act: -0.0001

Data Index: 249931 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0144. Min Act: -0.0001

Data Index: 1474693 (Python Code)

Max Activating Token Index: 28