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

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

Neuron 2909 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0002

Data Index: 405906 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0140. Min Act: -0.0002

Data Index: 542130 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1205411 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0140. Min Act: -0.0002

Data Index: 314447 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1170801 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1156401 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1082531 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1065206 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0002

Data Index: 440997 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0133. Min Act: -0.0002

Data Index: 886716 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0132. Min Act: -0.0002

Data Index: 844956 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1321229 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0133. Min Act: -0.0002

Data Index: 988627 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0002

Data Index: 804670 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0002

Data Index: 908889 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1349919 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 458932 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 494042 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1545125 (Python Code)

Max Activating Token Index: 388

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1053050 (C4 (Web Text))

Max Activating Token Index: 36