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

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

Neuron 3035 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4816. Min Act: -0.0000

Data Index: 478383 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.5075. Min Act: -0.0000

Data Index: 592526 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4992. Min Act: -0.0000

Data Index: 427029 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4578. Min Act: -0.0000

Data Index: 173432 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4415. Min Act: -0.0000

Data Index: 145446 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4237. Min Act: -0.0000

Data Index: 882474 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1253443 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1148089 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3854. Min Act: -0.0000

Data Index: 806063 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1175362 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4132. Min Act: -0.0000

Data Index: 483480 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3689. Min Act: -0.0000

Data Index: 766065 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3619. Min Act: -0.0000

Data Index: 638299 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3479. Min Act: -0.0000

Data Index: 194202 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1288543 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3593. Min Act: -0.0000

Data Index: 923308 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3584. Min Act: -0.0000

Data Index: 863949 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3320. Min Act: -0.0000

Data Index: 906105 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3570. Min Act: -0.0000

Data Index: 899921 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3537. Min Act: -0.0000

Data Index: 940140 (C4 (Web Text))

Max Activating Token Index: 872