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

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

Neuron 5857 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1635342 (Python Code)

Max Activating Token Index: 368

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1499036 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0838. Min Act: -0.0000

Data Index: 201580 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1403150 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1596541 (Python Code)

Max Activating Token Index: 573

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0600. Min Act: -0.0000

Data Index: 75610 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1636018 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0553. Min Act: -0.0000

Data Index: 471692 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1586778 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1229442 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1411638 (Python Code)

Max Activating Token Index: 383

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1566258 (Python Code)

Max Activating Token Index: 270

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1485887 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1542984 (Python Code)

Max Activating Token Index: 447

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1495676 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1063128 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1557803 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0506. Min Act: -0.0000

Data Index: 1421743 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1043812 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1400266 (Python Code)

Max Activating Token Index: 471