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

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

Neuron 4827 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.8504. Min Act: -0.0000

Data Index: 241878 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.6503. Min Act: -0.0000

Data Index: 1169995 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.7471. Min Act: -0.0000

Data Index: 1502719 (Python Code)

Max Activating Token Index: 628

Text #3

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.6861. Min Act: -0.0000

Data Index: 198066 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.5896. Min Act: -0.0000

Data Index: 270084 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.5838. Min Act: -0.0000

Data Index: 458151 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4189. Min Act: -0.0000

Data Index: 206719 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4735. Min Act: -0.0000

Data Index: 629460 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4401. Min Act: -0.0000

Data Index: 950523 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4001. Min Act: -0.0000

Data Index: 640767 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3945. Min Act: -0.0000

Data Index: 390779 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4705. Min Act: -0.0000

Data Index: 730152 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3407. Min Act: -0.0000

Data Index: 619716 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1624368 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4594. Min Act: -0.0000

Data Index: 365486 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3346. Min Act: -0.0000

Data Index: 878453 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3544. Min Act: -0.0000

Data Index: 1270403 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3948. Min Act: -0.0000

Data Index: 374824 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3523. Min Act: -0.0000

Data Index: 695458 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2928. Min Act: -0.0000

Data Index: 1562407 (Python Code)

Max Activating Token Index: 526