Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3999 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7721. Min Act: -0.0000

Data Index: 796413 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1448411 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5566. Min Act: -0.0000

Data Index: 437739 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1346037 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5726. Min Act: -0.0000

Data Index: 967305 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5798. Min Act: -0.0000

Data Index: 124710 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5436. Min Act: -0.0000

Data Index: 565893 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5188. Min Act: -0.0000

Data Index: 830959 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1842489 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1858690 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1255176 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4935. Min Act: -0.0000

Data Index: 513413 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1387610 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5055. Min Act: -0.0000

Data Index: 244039 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1171982 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1068436 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1194814 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.3930. Min Act: -0.0000

Data Index: 694393 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4647. Min Act: -0.0000

Data Index: 160068 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.3907. Min Act: -0.0000

Data Index: 664769 (The Pile)

Max Activating Token Index: 945