Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4596 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0556. Min Act: -0.0003

Data Index: 356984 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: -0.0003

Data Index: 610568 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0545. Min Act: -0.0003

Data Index: 993451 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1147535 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1053252 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0510. Min Act: -0.0003

Data Index: 791127 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0490. Min Act: -0.0003

Data Index: 751673 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0498. Min Act: -0.0003

Data Index: 8503 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1155582 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0494. Min Act: -0.0003

Data Index: 508671 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1028788 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0475. Min Act: -0.0003

Data Index: 526706 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1333500 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1160898 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0462. Min Act: -0.0003

Data Index: 850325 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0451. Min Act: -0.0002

Data Index: 836337 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1197580 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1297750 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0434. Min Act: -0.0003

Data Index: 329196 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1154747 (C4 (Web Text))

Max Activating Token Index: 127