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

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

Neuron 4875 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: 3.2425. Min Range: -3.2425

Max Act: 3.2425. Min Act: -0.0000

Data Index: 143612 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.7693. Min Act: -0.0000

Data Index: 395561 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.6089. Min Act: -0.0000

Data Index: 68170 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.4470. Min Act: -0.0000

Data Index: 432772 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.4352. Min Act: -0.0000

Data Index: 838914 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.4169. Min Act: -0.0000

Data Index: 677401 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.3257. Min Act: -0.0000

Data Index: 471677 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.1874. Min Act: -0.0000

Data Index: 1257171 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.2264. Min Act: -0.0000

Data Index: 561481 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.3459. Min Act: -0.0000

Data Index: 423633 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.1531. Min Act: -0.0000

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.0444. Min Act: -0.0000

Data Index: 823122 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.1322. Min Act: -0.0000

Data Index: 1012297 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.2573. Min Act: -0.0000

Data Index: 1236480 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.1023. Min Act: -0.0000

Data Index: 707526 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.2614. Min Act: -0.0000

Data Index: 735317 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.1024. Min Act: -0.0000

Data Index: 249409 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.2275. Min Act: -0.0000

Data Index: 1203249 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 3.2425. Min Range: -3.2425

Max Act: 1.9532. Min Act: -0.0000

Data Index: 801508 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 3.2425. Min Range: -3.2425

Max Act: 2.1644. Min Act: -0.0000

Data Index: 1252002 (C4 (Web Text))

Max Activating Token Index: 1016