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

Dataset: The Pile

Neuron 2512 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: 0.7114. Min Range: -0.7114

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1164863 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1902140 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.6939. Min Act: -0.0000

Data Index: 708566 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5703. Min Act: -0.0000

Data Index: 161671 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1961408 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5558. Min Act: -0.0000

Data Index: 779456 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5596. Min Act: -0.0000

Data Index: 74573 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1313016 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5120. Min Act: -0.0000

Data Index: 617909 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5270. Min Act: -0.0000

Data Index: 633657 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.4805. Min Act: -0.0000

Data Index: 139494 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5112. Min Act: -0.0000

Data Index: 350315 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.4491. Min Act: -0.0000

Data Index: 368241 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.4955. Min Act: -0.0000

Data Index: 845542 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5229. Min Act: -0.0000

Data Index: 624071 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5102. Min Act: -0.0000

Data Index: 903857 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.4805. Min Act: -0.0000

Data Index: 517233 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1818472 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1234991 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.7114. Min Range: -0.7114

Max Act: 0.4334. Min Act: -0.0000

Data Index: 273145 (The Pile)

Max Activating Token Index: 118