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

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

Neuron 3755 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.8561. Min Act: -0.0000

Data Index: 613509 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.7202. Min Act: -0.0000

Data Index: 572299 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.6535. Min Act: -0.0000

Data Index: 355027 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.7701. Min Act: -0.0000

Data Index: 765499 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.5678. Min Act: -0.0000

Data Index: 610174 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.4132. Min Act: -0.0000

Data Index: 1061072 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.5226. Min Act: -0.0000

Data Index: 904638 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.4163. Min Act: -0.0000

Data Index: 928882 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.3760. Min Act: -0.0000

Data Index: 1004975 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.1990. Min Act: -0.0000

Data Index: 786385 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.1956. Min Act: -0.0000

Data Index: 450371 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.4407. Min Act: -0.0000

Data Index: 831409 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.2077. Min Act: -0.0000

Data Index: 4173 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.2952. Min Act: -0.0000

Data Index: 763809 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.3792. Min Act: -0.0000

Data Index: 1280270 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.5272. Min Act: -0.0000

Data Index: 499607 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.1441. Min Act: -0.0000

Data Index: 59713 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.2235. Min Act: -0.0000

Data Index: 577733 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.2096. Min Act: -0.0000

Data Index: 423221 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 2.8561. Min Range: -2.8561

Max Act: 2.2109. Min Act: -0.0000

Data Index: 967549 (C4 (Web Text))

Max Activating Token Index: 95