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

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

Neuron 1707 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: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1552491 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0159. Min Act: -0.0006

Data Index: 758496 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1253519 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1221437 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0157. Min Act: -0.0006

Data Index: 911773 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0160. Min Act: -0.0006

Data Index: 918827 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1512820 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1178483 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1010306 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0153. Min Act: -0.0005

Data Index: 796235 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1258111 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1346781 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0151. Min Act: -0.0006

Data Index: 848589 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1588258 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1221856 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1611106 (Python Code)

Max Activating Token Index: 875

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0148. Min Act: -0.0006

Data Index: 853201 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0147. Min Act: -0.0006

Data Index: 342218 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0146. Min Act: -0.0006

Data Index: 566366 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0150. Min Act: -0.0005

Data Index: 207583 (C4 (Web Text))

Max Activating Token Index: 137