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

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

Neuron 385 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: 6.6207. Min Range: -6.6207

Max Act: 6.6207. Min Act: -0.0000

Data Index: 1517932 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 6.6207. Min Range: -6.6207

Max Act: 6.3548. Min Act: -0.0000

Data Index: 1502075 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 6.6207. Min Range: -6.6207

Max Act: 6.2553. Min Act: -0.0000

Data Index: 1567450 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 6.6207. Min Range: -6.6207

Max Act: 6.1084. Min Act: -0.0000

Data Index: 1520951 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 6.6207. Min Range: -6.6207

Max Act: 5.6665. Min Act: -0.0000

Data Index: 1618003 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 6.6207. Min Range: -6.6207

Max Act: 5.3991. Min Act: -0.0000

Data Index: 1373295 (Python Code)

Max Activating Token Index: 889

Text #6

Max Range: 6.6207. Min Range: -6.6207

Max Act: 5.3472. Min Act: -0.0000

Data Index: 1577665 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.9208. Min Act: -0.0000

Data Index: 1649935 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.8418. Min Act: -0.0000

Data Index: 1613399 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.9680. Min Act: -0.0000

Data Index: 1618245 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 6.6207. Min Range: -6.6207

Max Act: 5.1642. Min Act: -0.0000

Data Index: 1597204 (Python Code)

Max Activating Token Index: 524

Text #11

Max Range: 6.6207. Min Range: -6.6207

Max Act: 5.1038. Min Act: -0.0000

Data Index: 1561396 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.8243. Min Act: -0.0000

Data Index: 1624919 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 6.6207. Min Range: -6.6207

Max Act: 5.1543. Min Act: -0.0000

Data Index: 1609722 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.6070. Min Act: -0.0000

Data Index: 1409750 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 6.6207. Min Range: -6.6207

Max Act: 5.1308. Min Act: -0.0000

Data Index: 1484293 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.7473. Min Act: -0.0000

Data Index: 1654605 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.5692. Min Act: -0.0000

Data Index: 1575812 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.4689. Min Act: -0.0000

Data Index: 1510717 (Python Code)

Max Activating Token Index: 390

Text #19

Max Range: 6.6207. Min Range: -6.6207

Max Act: 4.4767. Min Act: -0.0000

Data Index: 1519142 (Python Code)

Max Activating Token Index: 202