Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1204 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0511. Min Act: -0.0003

Data Index: 19085 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0512. Min Act: -0.0003

Data Index: 31208 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0003

Data Index: 150601 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1317638 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0469. Min Act: -0.0002

Data Index: 871914 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1094975 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1004340 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0455. Min Act: -0.0003

Data Index: 263341 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0451. Min Act: -0.0003

Data Index: 246533 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0449. Min Act: -0.0002

Data Index: 162546 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0449. Min Act: -0.0002

Data Index: 938029 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0445. Min Act: -0.0004

Data Index: 1059952 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0433. Min Act: -0.0004

Data Index: 193940 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0447. Min Act: -0.0003

Data Index: 689400 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1213963 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0441. Min Act: 0.0001

Data Index: 442475 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0441. Min Act: -0.0003

Data Index: 301828 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0429. Min Act: -0.0003

Data Index: 771626 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1001616 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0420. Min Act: -0.0004

Data Index: 256636 (C4 (Web Text))

Max Activating Token Index: 816