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

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

Neuron 4928 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0002

Data Index: 399993 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0002

Data Index: 154161 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0002

Data Index: 648799 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0002

Data Index: 216733 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0002

Data Index: 235767 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1303333 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0002

Data Index: 211338 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1073268 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0149. Min Act: -0.0002

Data Index: 85136 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1354218 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1157505 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0150. Min Act: -0.0002

Data Index: 927371 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0150. Min Act: -0.0002

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0149. Min Act: -0.0002

Data Index: 513143 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0149. Min Act: -0.0002

Data Index: 191112 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1296596 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0148. Min Act: -0.0002

Data Index: 947247 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0148. Min Act: -0.0002

Data Index: 117447 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0147. Min Act: -0.0002

Data Index: 2692 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0146. Min Act: -0.0002

Data Index: 863273 (C4 (Web Text))

Max Activating Token Index: 675