Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4343 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7479. Min Act: -0.0001

Data Index: 408690 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7008. Min Act: -0.0001

Data Index: 576540 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6961. Min Act: -0.0001

Data Index: 736482 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7316. Min Act: -0.0000

Data Index: 800206 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6832. Min Act: -0.0000

Data Index: 476648 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6741. Min Act: -0.0000

Data Index: 750093 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1317257 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7096. Min Act: -0.0001

Data Index: 719406 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.5996. Min Act: -0.0000

Data Index: 103331 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1014694 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6156. Min Act: -0.0001

Data Index: 995448 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6782. Min Act: -0.0000

Data Index: 841406 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6459. Min Act: -0.0000

Data Index: 721925 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1031048 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6224. Min Act: -0.0000

Data Index: 876830 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6853. Min Act: -0.0001

Data Index: 994629 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6370. Min Act: -0.0000

Data Index: 404545 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6210. Min Act: -0.0000

Data Index: 738488 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6546. Min Act: -0.0000

Data Index: 504736 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6316. Min Act: -0.0000

Data Index: 593471 (C4 (Web Text))

Max Activating Token Index: 230