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

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

Neuron 2016 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0503. Min Range: -1.0503

Max Act: 1.0503. Min Act: -0.0000

Data Index: 764855 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1029922 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8269. Min Act: -0.0000

Data Index: 712462 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1195362 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8258. Min Act: -0.0000

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7552. Min Act: -0.0000

Data Index: 378934 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7583. Min Act: -0.0000

Data Index: 309325 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.8025. Min Act: -0.0000

Data Index: 573488 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1206287 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7521. Min Act: -0.0000

Data Index: 25220 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7693. Min Act: -0.0000

Data Index: 303948 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7587. Min Act: -0.0000

Data Index: 23825 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1275477 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7077. Min Act: -0.0000

Data Index: 431320 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.7081. Min Act: -0.0000

Data Index: 875338 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1064960 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.6576. Min Act: -0.0000

Data Index: 823206 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.6948. Min Act: -0.0000

Data Index: 913358 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.0503. Min Range: -1.0503

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 902