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

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

Neuron 2927 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.2785. Min Act: -0.0000

Data Index: 198156 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1132540 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.0282. Min Act: -0.0000

Data Index: 62963 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.9682. Min Act: -0.0001

Data Index: 158967 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.9826. Min Act: -0.0001

Data Index: 1008761 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.0191. Min Act: -0.0001

Data Index: 529982 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.2785. Min Range: -1.2785

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1151279 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.9479. Min Act: -0.0000

Data Index: 43921 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.9024. Min Act: -0.0001

Data Index: 658265 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1283378 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1050349 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1074173 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8654. Min Act: -0.0000

Data Index: 867724 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1058558 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8262. Min Act: -0.0000

Data Index: 763469 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8248. Min Act: -0.0000

Data Index: 780753 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8415. Min Act: -0.0000

Data Index: 270402 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1131933 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1333190 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.2785. Min Range: -1.2785

Max Act: 0.8318. Min Act: -0.0001

Data Index: 460496 (C4 (Web Text))

Max Activating Token Index: 128