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

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

Neuron 67 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0001

Data Index: 426463 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0177. Min Act: -0.0001

Data Index: 852846 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0185. Min Act: -0.0001

Data Index: 339827 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0175. Min Act: -0.0001

Data Index: 119978 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0174. Min Act: -0.0001

Data Index: 253304 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1278899 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0182. Min Act: -0.0001

Data Index: 273597 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0175. Min Act: -0.0001

Data Index: 115804 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0163. Min Act: -0.0001

Data Index: 944824 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0168. Min Act: -0.0001

Data Index: 121706 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0174. Min Act: -0.0001

Data Index: 63021 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0173. Min Act: -0.0001

Data Index: 447126 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0164. Min Act: -0.0001

Data Index: 769631 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0144. Min Act: -0.0001

Data Index: 297194 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0164. Min Act: -0.0001

Data Index: 552660 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0155. Min Act: -0.0001

Data Index: 1559248 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0159. Min Act: -0.0001

Data Index: 1259519 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0161. Min Act: -0.0001

Data Index: 389680 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1040812 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0160. Min Act: -0.0001

Data Index: 276583 (C4 (Web Text))

Max Activating Token Index: 210