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

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

Neuron 3503 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1339347 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7127. Min Act: -0.0000

Data Index: 539729 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7102. Min Act: -0.0000

Data Index: 488645 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7028. Min Act: 0.0000

Data Index: 309406 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6660. Min Act: -0.0000

Data Index: 410003 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6474. Min Act: -0.0000

Data Index: 568412 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6824. Min Act: -0.0000

Data Index: 267936 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6842. Min Act: -0.0000

Data Index: 401158 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6678. Min Act: -0.0000

Data Index: 607808 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6371. Min Act: -0.0000

Data Index: 35342 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6498. Min Act: -0.0000

Data Index: 586014 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1253619 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6147. Min Act: -0.0000

Data Index: 204374 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1047807 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1165644 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5663. Min Act: -0.0000

Data Index: 668554 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5754. Min Act: -0.0000

Data Index: 7915 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5685. Min Act: -0.0000

Data Index: 143017 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1146542 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5760. Min Act: -0.0000

Data Index: 65516 (C4 (Web Text))

Max Activating Token Index: 989