Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4984. Min Act: -0.0000

Data Index: 564065 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1190090 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1347386 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4009. Min Act: -0.0000

Data Index: 826717 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4276. Min Act: -0.0001

Data Index: 631587 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4115. Min Act: -0.0000

Data Index: 915403 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4130. Min Act: -0.0000

Data Index: 649858 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3767. Min Act: -0.0000

Data Index: 490030 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3792. Min Act: -0.0000

Data Index: 722965 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3350. Min Act: -0.0000

Data Index: 842521 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3014. Min Act: -0.0000

Data Index: 917450 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3313. Min Act: -0.0000

Data Index: 428643 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1286743 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.2947. Min Act: -0.0000

Data Index: 792064 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1331020 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3208. Min Act: -0.0000

Data Index: 529243 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1083536 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3037. Min Act: -0.0000

Data Index: 607989 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3194. Min Act: -0.0000

Data Index: 852257 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.2722. Min Act: -0.0001

Data Index: 528328 (C4 (Web Text))

Max Activating Token Index: 106