Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1346 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0005

Data Index: 312238 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0164. Min Act: -0.0005

Data Index: 1218786 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0153. Min Act: -0.0005

Data Index: 615348 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0005

Data Index: 503440 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0154. Min Act: -0.0005

Data Index: 857098 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0150. Min Act: -0.0005

Data Index: 1248352 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0150. Min Act: -0.0005

Data Index: 281214 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0156. Min Act: -0.0005

Data Index: 942546 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0153. Min Act: -0.0005

Data Index: 355971 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1177525 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0155. Min Act: -0.0005

Data Index: 100499 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0005

Data Index: 957259 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0138. Min Act: -0.0005

Data Index: 223610 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0147. Min Act: -0.0005

Data Index: 722735 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0150. Min Act: -0.0005

Data Index: 66862 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0144. Min Act: -0.0005

Data Index: 753365 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0005

Data Index: 2748 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0146. Min Act: -0.0005

Data Index: 351567 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0005

Data Index: 982981 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0155. Min Act: -0.0005

Data Index: 957265 (C4 (Web Text))

Max Activating Token Index: 893