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

Dataset: The Pile

Neuron 13 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: 1.1350. Min Range: -1.1350

Max Act: 1.1217. Min Act: -0.0000

Data Index: 783802 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1302851 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1348241 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1897789 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0249. Min Act: -0.0000

Data Index: 68666 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9180. Min Act: -0.0000

Data Index: 563710 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9376. Min Act: -0.0000

Data Index: 948696 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1147405 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1319450 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9118. Min Act: -0.0000

Data Index: 38281 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1299165 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8578. Min Act: -0.0000

Data Index: 482936 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8538. Min Act: -0.0000

Data Index: 4359 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8439. Min Act: -0.0000

Data Index: 74358 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1973105 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8130. Min Act: -0.0000

Data Index: 428690 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8108. Min Act: -0.0000

Data Index: 425624 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.7880. Min Act: -0.0000

Data Index: 343902 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1953990 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1125576 (The Pile)

Max Activating Token Index: 429