Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 178 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1164868 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0169. Min Act: -0.0003

Data Index: 289718 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1309124 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0157. Min Act: -0.0003

Data Index: 151605 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0147. Min Act: -0.0003

Data Index: 771900 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1442591 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0151. Min Act: -0.0003

Data Index: 683794 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1195303 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1014714 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1177232 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1018604 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0145. Min Act: -0.0003

Data Index: 309206 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0147. Min Act: -0.0003

Data Index: 628516 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1429850 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0155. Min Act: -0.0003

Data Index: 485866 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0147. Min Act: -0.0003

Data Index: 456690 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1186705 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0142. Min Act: -0.0003

Data Index: 102077 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0131. Min Act: -0.0003

Data Index: 936440 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0131. Min Act: -0.0003

Data Index: 447124 (C4 (Web Text))

Max Activating Token Index: 2