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

Dataset: The Pile

Neuron 2337 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: 0.7952. Min Range: -0.7952

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1227952 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1308700 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6369. Min Act: -0.0000

Data Index: 832904 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1767725 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.6258. Min Act: -0.0000

Data Index: 827852 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5181. Min Act: -0.0000

Data Index: 732632 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5725. Min Act: -0.0000

Data Index: 31511 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1306962 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5471. Min Act: -0.0000

Data Index: 870804 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5872. Min Act: -0.0000

Data Index: 828157 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1454396 (The Pile)

Max Activating Token Index: 405

Text #11

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1911706 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5635. Min Act: -0.0000

Data Index: 113092 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5642. Min Act: -0.0000

Data Index: 920211 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5585. Min Act: -0.0000

Data Index: 974443 (The Pile)

Max Activating Token Index: 515

Text #15

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1230967 (The Pile)

Max Activating Token Index: 738

Text #16

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1824908 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5533. Min Act: -0.0000

Data Index: 614667 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1840648 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 0.7952. Min Range: -0.7952

Max Act: 0.5413. Min Act: -0.0000

Data Index: 993834 (The Pile)

Max Activating Token Index: 251