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

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

Neuron 4571 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.7274. Min Act: -0.0000

Data Index: 123034 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5929. Min Act: -0.0000

Data Index: 49560 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1074473 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1180491 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1068649 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5072. Min Act: -0.0000

Data Index: 764426 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5274. Min Act: -0.0000

Data Index: 767365 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4971. Min Act: -0.0000

Data Index: 209849 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1122223 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4587. Min Act: -0.0000

Data Index: 802089 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4722. Min Act: -0.0000

Data Index: 892306 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4504. Min Act: -0.0000

Data Index: 812041 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4831. Min Act: -0.0000

Data Index: 142927 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4783. Min Act: -0.0000

Data Index: 498359 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4451. Min Act: -0.0000

Data Index: 826266 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4736. Min Act: -0.0000

Data Index: 595852 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4598. Min Act: -0.0000

Data Index: 521664 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4711. Min Act: -0.0000

Data Index: 982536 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1286651 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1035194 (C4 (Web Text))

Max Activating Token Index: 585