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

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

Neuron 4649 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0143. Min Act: -0.0002

Data Index: 583945 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1271940 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0156. Min Act: -0.0002

Data Index: 130812 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0150. Min Act: -0.0002

Data Index: 752105 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0140. Min Act: -0.0002

Data Index: 876014 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0133. Min Act: -0.0002

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0145. Min Act: -0.0002

Data Index: 29206 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0144. Min Act: -0.0002

Data Index: 93559 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0133. Min Act: -0.0002

Data Index: 660671 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1370395 (Python Code)

Max Activating Token Index: 85

Text #10

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1428746 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0139. Min Act: -0.0002

Data Index: 994414 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1123969 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1237803 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0140. Min Act: -0.0002

Data Index: 190118 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1219810 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0122. Min Act: -0.0002

Data Index: 420871 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0128. Min Act: -0.0002

Data Index: 981332 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1536169 (Python Code)

Max Activating Token Index: 231

Text #19

Max Range: 0.0156. Min Range: -0.0156

Max Act: 0.0125. Min Act: -0.0002

Data Index: 597936 (C4 (Web Text))

Max Activating Token Index: 333