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

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

Neuron 3072 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.6466. Min Act: -0.0000

Data Index: 1270679 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.5914. Min Act: -0.0000

Data Index: 546390 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.5559. Min Act: -0.0000

Data Index: 559495 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1257023 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.2210. Min Act: -0.0000

Data Index: 286940 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.0374. Min Act: -0.0000

Data Index: 726893 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.0221. Min Act: -0.0000

Data Index: 808874 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.0264. Min Act: -0.0000

Data Index: 18253 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9994. Min Act: -0.0000

Data Index: 94614 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.0211. Min Act: -0.0000

Data Index: 838846 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9481. Min Act: -0.0000

Data Index: 748571 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9966. Min Act: -0.0000

Data Index: 864865 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1103675 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9478. Min Act: -0.0000

Data Index: 273304 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9545. Min Act: -0.0000

Data Index: 973382 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9808. Min Act: -0.0000

Data Index: 965901 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9656. Min Act: -0.0000

Data Index: 940468 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1340352 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9462. Min Act: -0.0000

Data Index: 739191 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.6466. Min Range: -1.6466

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1109169 (C4 (Web Text))

Max Activating Token Index: 621