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

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

Neuron 3763 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: 4.0966. Min Range: -4.0966

Max Act: 3.7063. Min Act: -0.0000

Data Index: 216994 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 4.0966. Min Range: -4.0966

Max Act: 4.0966. Min Act: -0.0000

Data Index: 1334587 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.5047. Min Act: -0.0000

Data Index: 365554 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.6227. Min Act: -0.0000

Data Index: 930269 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.2652. Min Act: -0.0000

Data Index: 827011 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.4543. Min Act: -0.0000

Data Index: 652063 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.5938. Min Act: -0.0000

Data Index: 981131 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.1561. Min Act: -0.0000

Data Index: 349251 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.4871. Min Act: -0.0000

Data Index: 763929 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.3485. Min Act: -0.0000

Data Index: 344498 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.6391. Min Act: -0.0000

Data Index: 974666 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.4271. Min Act: -0.0000

Data Index: 384580 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.5938. Min Act: -0.0000

Data Index: 1048082 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.2903. Min Act: -0.0000

Data Index: 847391 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.6189. Min Act: -0.0000

Data Index: 441336 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.5334. Min Act: -0.0000

Data Index: 690715 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.3245. Min Act: -0.0000

Data Index: 854389 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.3643. Min Act: -0.0000

Data Index: 446328 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.4647. Min Act: -0.0000

Data Index: 1113191 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 4.0966. Min Range: -4.0966

Max Act: 3.1938. Min Act: -0.0000

Data Index: 1004469 (C4 (Web Text))

Max Activating Token Index: 902