Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 55 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0166. Min Act: -0.0004

Data Index: 87575 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0145. Min Act: -0.0004

Data Index: 803629 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0164. Min Act: -0.0004

Data Index: 402503 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0157. Min Act: -0.0004

Data Index: 883358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0156. Min Act: -0.0004

Data Index: 86703 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1110118 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0163. Min Act: -0.0004

Data Index: 749571 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0152. Min Act: -0.0004

Data Index: 523473 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0154. Min Act: -0.0004

Data Index: 868360 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0004

Data Index: 169205 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0004

Data Index: 43656 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0149. Min Act: -0.0004

Data Index: 549472 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0121. Min Act: -0.0004

Data Index: 510699 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0144. Min Act: -0.0004

Data Index: 278758 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0136. Min Act: -0.0004

Data Index: 721626 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0136. Min Act: -0.0004

Data Index: 490011 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1102749 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0147. Min Act: -0.0004

Data Index: 566334 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0150. Min Act: -0.0004

Data Index: 1252767 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0147. Min Act: -0.0004

Data Index: 967790 (C4 (Web Text))

Max Activating Token Index: 431