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

Dataset: The Pile

Neuron 2221 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.6550. Min Act: -0.0000

Data Index: 1132920 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.7325. Min Act: -0.0000

Data Index: 279341 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.3216. Min Act: -0.0000

Data Index: 450234 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.1850. Min Act: -0.0000

Data Index: 1480408 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.3294. Min Act: -0.0000

Data Index: 214980 (The Pile)

Max Activating Token Index: 8

Text #5

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.9979. Min Act: -0.0000

Data Index: 95107 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.9545. Min Act: -0.0000

Data Index: 200957 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.0793. Min Act: -0.0000

Data Index: 1492702 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.0542. Min Act: -0.0000

Data Index: 1872209 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.0314. Min Act: -0.0000

Data Index: 1041334 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.0159. Min Act: -0.0000

Data Index: 1694614 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 5.7325. Min Range: -5.7325

Max Act: 5.0433. Min Act: -0.0000

Data Index: 1840431 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.5406. Min Act: -0.0000

Data Index: 827258 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.8244. Min Act: -0.0000

Data Index: 1351034 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.8155. Min Act: -0.0000

Data Index: 969508 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.7738. Min Act: -0.0000

Data Index: 829678 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.9481. Min Act: -0.0000

Data Index: 473358 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.8629. Min Act: -0.0000

Data Index: 1878079 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.8638. Min Act: -0.0000

Data Index: 120609 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 5.7325. Min Range: -5.7325

Max Act: 4.7134. Min Act: -0.0000

Data Index: 1200920 (The Pile)

Max Activating Token Index: 11