Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8467. Min Act: -0.0000

Data Index: 231974 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8468. Min Act: -0.0001

Data Index: 1123082 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7922. Min Act: -0.0000

Data Index: 173662 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8330. Min Act: -0.0000

Data Index: 641761 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8639. Min Act: -0.0000

Data Index: 557126 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1056008 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8032. Min Act: -0.0001

Data Index: 397519 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1061227 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8258. Min Act: -0.0001

Data Index: 120359 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1055448 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8155. Min Act: -0.0001

Data Index: 765248 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7602. Min Act: -0.0001

Data Index: 1074630 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.8206. Min Act: -0.0000

Data Index: 233365 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7737. Min Act: -0.0001

Data Index: 848543 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1104848 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7851. Min Act: -0.0000

Data Index: 382675 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1224185 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1319033 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7774. Min Act: -0.0000

Data Index: 813711 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.8639. Min Range: -0.8639

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1209880 (C4 (Web Text))

Max Activating Token Index: 893