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

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

Neuron 578 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1190275 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0169. Min Act: -0.0003

Data Index: 187931 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0152. Min Act: -0.0003

Data Index: 889268 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0155. Min Act: -0.0003

Data Index: 665451 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1178981 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0153. Min Act: -0.0004

Data Index: 406001 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0153. Min Act: -0.0004

Data Index: 757984 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0146. Min Act: -0.0004

Data Index: 81143 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0148. Min Act: -0.0004

Data Index: 951768 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0147. Min Act: -0.0003

Data Index: 950818 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1352972 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0149. Min Act: -0.0003

Data Index: 382704 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1026473 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0143. Min Act: -0.0004

Data Index: 525880 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0143. Min Act: -0.0004

Data Index: 225463 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0142. Min Act: -0.0003

Data Index: 190507 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0143. Min Act: -0.0004

Data Index: 65206 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0142. Min Act: -0.0003

Data Index: 632379 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0141. Min Act: -0.0003

Data Index: 574907 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1347752 (C4 (Web Text))

Max Activating Token Index: 963