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

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

Neuron 2502 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: 1336142 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0142. Min Act: -0.0002

Data Index: 998496 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0139. Min Act: -0.0002

Data Index: 898646 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0136. Min Act: -0.0002

Data Index: 880983 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0137. Min Act: -0.0002

Data Index: 476242 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0002

Data Index: 922367 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0002

Data Index: 742977 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0002

Data Index: 674121 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0002

Data Index: 534470 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1069174 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 101748 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 531568 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0002

Data Index: 95617 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1089450 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0002

Data Index: 990645 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0002

Data Index: 466204 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0002

Data Index: 55808 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0002

Data Index: 501978 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0002

Data Index: 447588 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0002

Data Index: 980520 (C4 (Web Text))

Max Activating Token Index: 16