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

Dataset: The Pile

Neuron 1098 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: 1.1249. Min Range: -1.1249

Max Act: 1.1249. Min Act: -0.0000

Data Index: 1633975 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1064150 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9766. Min Act: -0.0000

Data Index: 312264 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1796156 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.9169. Min Act: -0.0000

Data Index: 945159 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8986. Min Act: -0.0000

Data Index: 490879 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1028755 (The Pile)

Max Activating Token Index: 11

Text #7

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8522. Min Act: -0.0000

Data Index: 292717 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8517. Min Act: -0.0000

Data Index: 878063 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1588388 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7862. Min Act: -0.0000

Data Index: 768529 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1198236 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8261. Min Act: -0.0000

Data Index: 626285 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8089. Min Act: -0.0000

Data Index: 836353 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1649419 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1370542 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1959209 (The Pile)

Max Activating Token Index: 291

Text #17

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1043193 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1345459 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 1.1249. Min Range: -1.1249

Max Act: 0.8130. Min Act: -0.0000

Data Index: 706933 (The Pile)

Max Activating Token Index: 935