Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 106 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0154. Min Act: -0.0006

Data Index: 974241 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1188601 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1117812 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0006

Data Index: 676210 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0154. Min Act: -0.0006

Data Index: 909113 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 179311 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 119842 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1191869 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0149. Min Act: -0.0006

Data Index: 838895 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0149. Min Act: -0.0006

Data Index: 723428 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0006

Data Index: 58610 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0006

Data Index: 64603 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1135648 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0006

Data Index: 30034 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1009826 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1152255 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 254619 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 389751 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 831368 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1141725 (C4 (Web Text))

Max Activating Token Index: 23