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

Dataset: The Pile

Neuron 3520 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4835. Min Act: -0.0000

Data Index: 181191 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1773921 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1673939 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4497. Min Act: -0.0000

Data Index: 854267 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1577111 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1333948 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3327. Min Act: -0.0000

Data Index: 594289 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3378. Min Act: -0.0000

Data Index: 754941 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1109573 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1205078 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3536. Min Act: -0.0000

Data Index: 758735 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3535. Min Act: -0.0000

Data Index: 108364 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1469999 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1966577 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1344882 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1196827 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1495099 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3267. Min Act: -0.0000

Data Index: 998663 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3277. Min Act: -0.0000

Data Index: 799940 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 0.4835. Min Range: -0.4835

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1080450 (The Pile)

Max Activating Token Index: 947