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

Dataset: The Pile

Neuron 2822 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: 0.6888. Min Range: -0.6888

Max Act: 0.6888. Min Act: -0.0000

Data Index: 298597 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1871956 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6293. Min Act: -0.0000

Data Index: 836873 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6445. Min Act: 0.0003

Data Index: 1413740 (The Pile)

Max Activating Token Index: 633

Text #4

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6064. Min Act: -0.0000

Data Index: 913960 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5775. Min Act: -0.0000

Data Index: 49529 (The Pile)

Max Activating Token Index: 291

Text #6

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5821. Min Act: -0.0000

Data Index: 235189 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5187. Min Act: 0.0001

Data Index: 1461148 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1049583 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4901. Min Act: -0.0000

Data Index: 721560 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4829. Min Act: 0.0000

Data Index: 824636 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4946. Min Act: 0.0000

Data Index: 706662 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1479368 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1850543 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1356643 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1577853 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4877. Min Act: -0.0000

Data Index: 581224 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1213101 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4860. Min Act: 0.0000

Data Index: 1375611 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4566. Min Act: -0.0000

Data Index: 275534 (The Pile)

Max Activating Token Index: 619