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

Dataset: The Pile

Neuron 1131 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1245608 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9780. Min Act: -0.0000

Data Index: 674628 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.0418. Min Act: -0.0000

Data Index: 279585 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9573. Min Act: -0.0000

Data Index: 806189 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1513355 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9844. Min Act: -0.0000

Data Index: 904024 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9960. Min Act: -0.0000

Data Index: 258096 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1426112 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9472. Min Act: -0.0000

Data Index: 549121 (The Pile)

Max Activating Token Index: 100

Text #9

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9598. Min Act: -0.0000

Data Index: 704172 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9364. Min Act: -0.0000

Data Index: 549239 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1447821 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9188. Min Act: -0.0000

Data Index: 157386 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9453. Min Act: -0.0000

Data Index: 323013 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8990. Min Act: -0.0000

Data Index: 932059 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1903402 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8958. Min Act: -0.0001

Data Index: 1226874 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9181. Min Act: -0.0000

Data Index: 633858 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9175. Min Act: -0.0000

Data Index: 273340 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8454. Min Act: -0.0000

Data Index: 377257 (The Pile)

Max Activating Token Index: 988