Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 782 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.5511. Min Act: -0.0001

Data Index: 738804 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.5109. Min Act: -0.0001

Data Index: 491668 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4857. Min Act: -0.0001

Data Index: 574161 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4953. Min Act: -0.0001

Data Index: 495851 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.5119. Min Act: -0.0001

Data Index: 1149479 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.5508. Min Act: -0.0001

Data Index: 1138437 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1062795 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4650. Min Act: -0.0001

Data Index: 554449 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4810. Min Act: -0.0001

Data Index: 553086 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4532. Min Act: -0.0001

Data Index: 453764 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4453. Min Act: -0.0001

Data Index: 779090 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4456. Min Act: -0.0001

Data Index: 1126117 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4432. Min Act: -0.0001

Data Index: 667986 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4712. Min Act: -0.0001

Data Index: 701856 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4550. Min Act: -0.0001

Data Index: 1090816 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4510. Min Act: -0.0001

Data Index: 442331 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4351. Min Act: -0.0001

Data Index: 581647 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4446. Min Act: -0.0001

Data Index: 763605 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4292. Min Act: -0.0001

Data Index: 33143 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.5511. Min Range: -0.5511

Max Act: 0.4583. Min Act: -0.0001

Data Index: 733555 (C4 (Web Text))

Max Activating Token Index: 976