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

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

Neuron 2869 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0003

Data Index: 886204 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1348956 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1347175 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0163. Min Act: -0.0003

Data Index: 235429 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0162. Min Act: -0.0003

Data Index: 487630 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0130. Min Act: -0.0003

Data Index: 407512 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0156. Min Act: -0.0003

Data Index: 517094 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0159. Min Act: -0.0003

Data Index: 539686 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1109605 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0145. Min Act: -0.0003

Data Index: 121481 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1051164 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0139. Min Act: -0.0003

Data Index: 36292 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0155. Min Act: -0.0003

Data Index: 941649 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0145. Min Act: -0.0003

Data Index: 149003 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0148. Min Act: -0.0003

Data Index: 559541 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0129. Min Act: -0.0003

Data Index: 389994 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0146. Min Act: -0.0003

Data Index: 294708 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0155. Min Act: -0.0003

Data Index: 289853 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0140. Min Act: -0.0003

Data Index: 211828 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0128. Min Act: -0.0003

Data Index: 912097 (C4 (Web Text))

Max Activating Token Index: 819