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

Dataset: The Pile

Neuron 1655 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.3923. Min Act: 0.0000

Data Index: 632339 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1325618 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.1027. Min Act: 0.0000

Data Index: 1310925 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.0761. Min Act: -0.0000

Data Index: 834618 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1656436 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 1.3923. Min Range: -1.3923

Max Act: 1.0521. Min Act: 0.0000

Data Index: 742344 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1773501 (The Pile)

Max Activating Token Index: 826

Text #7

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8650. Min Act: -0.0000

Data Index: 492323 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1227746 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1449858 (The Pile)

Max Activating Token Index: 247

Text #10

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.9018. Min Act: -0.0000

Data Index: 667826 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1548399 (The Pile)

Max Activating Token Index: 101

Text #12

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8543. Min Act: 0.0000

Data Index: 1549884 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7926. Min Act: 0.0000

Data Index: 1905009 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.8604. Min Act: -0.0000

Data Index: 467149 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7226. Min Act: 0.0000

Data Index: 679681 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7672. Min Act: -0.0000

Data Index: 495909 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7210. Min Act: -0.0000

Data Index: 567241 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1815552 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 1.3923. Min Range: -1.3923

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1679655 (The Pile)

Max Activating Token Index: 853