Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 584 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1570890 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1048367 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1012288 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0180. Min Act: -0.0001

Data Index: 423377 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0169. Min Act: -0.0001

Data Index: 967546 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1397752 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0150. Min Act: -0.0001

Data Index: 579936 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1441501 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0163. Min Act: -0.0001

Data Index: 1228648 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0147. Min Act: -0.0001

Data Index: 573671 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1433654 (Python Code)

Max Activating Token Index: 78

Text #11

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0169. Min Act: -0.0001

Data Index: 683018 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1026988 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0166. Min Act: -0.0001

Data Index: 737025 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1602746 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0151. Min Act: -0.0001

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0158. Min Act: -0.0001

Data Index: 939683 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0156. Min Act: -0.0001

Data Index: 419678 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0152. Min Act: -0.0001

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0157. Min Act: -0.0001

Data Index: 256944 (C4 (Web Text))

Max Activating Token Index: 222