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

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

Neuron 4295 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.8436. Min Range: -10.8436

Max Act: 10.8436. Min Act: -0.0000

Data Index: 1212724 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 10.8436. Min Range: -10.8436

Max Act: 10.5919. Min Act: -0.0000

Data Index: 485117 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 10.8436. Min Range: -10.8436

Max Act: 10.1959. Min Act: -0.0000

Data Index: 1147084 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 10.8436. Min Range: -10.8436

Max Act: 10.0514. Min Act: -0.0000

Data Index: 1335416 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.9590. Min Act: -0.0000

Data Index: 1229775 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.8632. Min Act: -0.0000

Data Index: 1019712 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.6858. Min Act: -0.0000

Data Index: 854599 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.6673. Min Act: -0.0000

Data Index: 13944 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.9486. Min Act: -0.0000

Data Index: 337160 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.2655. Min Act: -0.0000

Data Index: 695379 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.2392. Min Act: -0.0000

Data Index: 1026948 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.2565. Min Act: -0.0000

Data Index: 168568 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.2075. Min Act: -0.0000

Data Index: 1285104 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.1485. Min Act: -0.0000

Data Index: 466854 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.3014. Min Act: -0.0000

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.3109. Min Act: -0.0000

Data Index: 1140438 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.0303. Min Act: -0.0000

Data Index: 1226169 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 10.8436. Min Range: -10.8436

Max Act: 8.9672. Min Act: -0.0000

Data Index: 661497 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.2346. Min Act: -0.0000

Data Index: 827780 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 10.8436. Min Range: -10.8436

Max Act: 9.3073. Min Act: -0.0000

Data Index: 1182305 (C4 (Web Text))

Max Activating Token Index: 1004