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

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

Neuron 2551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.6735. Min Act: -0.0000

Data Index: 680145 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.7528. Min Act: -0.0000

Data Index: 559917 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.6947. Min Act: -0.0000

Data Index: 41893 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.5544. Min Act: -0.0000

Data Index: 653439 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.5239. Min Act: -0.0000

Data Index: 511599 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.7536. Min Act: -0.0000

Data Index: 705401 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1314608 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.4314. Min Act: -0.0000

Data Index: 930497 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.3929. Min Act: -0.0000

Data Index: 431164 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1046643 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.4385. Min Act: -0.0000

Data Index: 1055713 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.5118. Min Act: -0.0000

Data Index: 608683 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.4780. Min Act: -0.0000

Data Index: 788971 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.4308. Min Act: -0.0000

Data Index: 512646 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1237428 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.3139. Min Act: -0.0000

Data Index: 289188 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.3025. Min Act: -0.0000

Data Index: 955360 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.3621. Min Act: -0.0000

Data Index: 805861 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.3238. Min Act: -0.0000

Data Index: 933861 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.2755. Min Act: -0.0000

Data Index: 847019 (C4 (Web Text))

Max Activating Token Index: 483