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

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

Neuron 2585 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0001

Data Index: 589399 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0151. Min Act: -0.0001

Data Index: 194622 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0153. Min Act: -0.0001

Data Index: 262231 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0164. Min Act: -0.0001

Data Index: 825734 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0156. Min Act: -0.0002

Data Index: 401911 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0138. Min Act: -0.0001

Data Index: 854450 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0139. Min Act: -0.0001

Data Index: 424539 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0151. Min Act: -0.0002

Data Index: 147210 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0111. Min Act: -0.0002

Data Index: 954379 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1185200 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0144. Min Act: -0.0001

Data Index: 617266 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0119. Min Act: -0.0002

Data Index: 609403 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0122. Min Act: -0.0001

Data Index: 333956 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1070332 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0136. Min Act: -0.0001

Data Index: 631131 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1084362 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1203121 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0156. Min Act: -0.0001

Data Index: 167395 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0133. Min Act: -0.0001

Data Index: 857186 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1313238 (C4 (Web Text))

Max Activating Token Index: 309