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

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

Neuron 622 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: 3.9294. Min Range: -3.9294

Max Act: 3.8458. Min Act: -0.0000

Data Index: 405120 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.9294. Min Act: -0.0000

Data Index: 1198248 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.7615. Min Act: -0.0000

Data Index: 602692 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.8116. Min Act: -0.0000

Data Index: 1209465 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.3382. Min Act: -0.0000

Data Index: 1171137 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.3497. Min Act: 0.0000

Data Index: 610844 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.4052. Min Act: -0.0000

Data Index: 612871 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.3556. Min Act: -0.0000

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.3099. Min Act: -0.0000

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.2303. Min Act: -0.0000

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.2142. Min Act: -0.0000

Data Index: 437136 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.0486. Min Act: -0.0000

Data Index: 1244466 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.0058. Min Act: -0.0000

Data Index: 73093 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.9935. Min Act: -0.0000

Data Index: 1315223 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.2684. Min Act: -0.0000

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.0922. Min Act: -0.0000

Data Index: 1311610 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.2086. Min Act: -0.0000

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.8965. Min Act: -0.0000

Data Index: 989420 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.0869. Min Act: -0.0000

Data Index: 884769 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.3405. Min Act: -0.0000

Data Index: 778660 (C4 (Web Text))

Max Activating Token Index: 551