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

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

Neuron 5692 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.7581. Min Act: -0.0000

Data Index: 435022 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.5670. Min Act: -0.0000

Data Index: 1555214 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.6655. Min Act: -0.0000

Data Index: 659850 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.4817. Min Act: -0.0000

Data Index: 828536 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.0286. Min Act: -0.0000

Data Index: 1632360 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.4943. Min Act: -0.0000

Data Index: 1260464 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.3578. Min Act: -0.0000

Data Index: 1377208 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.2193. Min Act: -0.0000

Data Index: 1464835 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.2304. Min Act: -0.0000

Data Index: 559882 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.1353. Min Act: -0.0000

Data Index: 1570087 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 2.7581. Min Range: -2.7581

Max Act: 2.2062. Min Act: -0.0000

Data Index: 1567583 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.9438. Min Act: -0.0000

Data Index: 1479345 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.9944. Min Act: -0.0000

Data Index: 347287 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.8797. Min Act: -0.0000

Data Index: 1224534 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.9251. Min Act: -0.0000

Data Index: 1616536 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.8128. Min Act: -0.0000

Data Index: 1478135 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.9095. Min Act: -0.0000

Data Index: 1431001 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.8719. Min Act: -0.0000

Data Index: 1580763 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.8560. Min Act: -0.0000

Data Index: 1535025 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 2.7581. Min Range: -2.7581

Max Act: 1.7465. Min Act: -0.0000

Data Index: 1534469 (Python Code)

Max Activating Token Index: 220