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

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

Neuron 1578 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: 0.0552. Min Range: -0.0552

Max Act: 0.0552. Min Act: -0.0000

Data Index: 981590 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1424865 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0471. Min Act: -0.0000

Data Index: 133239 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0490. Min Act: -0.0000

Data Index: 788944 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1604122 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1402212 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0421. Min Act: -0.0000

Data Index: 708413 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1596283 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0433. Min Act: -0.0000

Data Index: 724359 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0442. Min Act: -0.0000

Data Index: 886988 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0440. Min Act: -0.0000

Data Index: 655706 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0425. Min Act: -0.0000

Data Index: 986828 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0380. Min Act: -0.0000

Data Index: 30177 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1553654 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0417. Min Act: -0.0000

Data Index: 352666 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1635794 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0414. Min Act: -0.0000

Data Index: 1447782 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1650998 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0412. Min Act: -0.0000

Data Index: 1560300 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0394. Min Act: -0.0000

Data Index: 152531 (C4 (Web Text))

Max Activating Token Index: 105