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

Dataset: The Pile

Neuron 42 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.9313. Min Act: -0.0000

Data Index: 422006 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.7619. Min Act: -0.0000

Data Index: 1660581 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.7310. Min Act: -0.0000

Data Index: 732557 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6915. Min Act: -0.0000

Data Index: 1845602 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6872. Min Act: -0.0000

Data Index: 322949 (The Pile)

Max Activating Token Index: 164

Text #5

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6574. Min Act: -0.0000

Data Index: 1266986 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6532. Min Act: -0.0000

Data Index: 308313 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1759301 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1918775 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6187. Min Act: -0.0000

Data Index: 1423128 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.5709. Min Act: -0.0000

Data Index: 1770858 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.5038. Min Act: -0.0000

Data Index: 1203202 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.4862. Min Act: -0.0000

Data Index: 951014 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.4894. Min Act: -0.0000

Data Index: 1274243 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.5873. Min Act: -0.0000

Data Index: 477493 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1566116 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.6457. Min Act: -0.0000

Data Index: 1296514 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.4713. Min Act: -0.0000

Data Index: 970902 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.5515. Min Act: -0.0000

Data Index: 658850 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 1.9313. Min Range: -1.9313

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1387761 (The Pile)

Max Activating Token Index: 13