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

Dataset: The Pile

Neuron 1046 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.5249. Min Act: -0.0000

Data Index: 810321 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1830147 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3602. Min Act: 0.0000

Data Index: 818795 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1091661 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3656. Min Act: -0.0000

Data Index: 62074 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1122811 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3623. Min Act: -0.0000

Data Index: 875069 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1221023 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3674. Min Act: 0.0000

Data Index: 186175 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1259415 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1709040 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1650957 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3251. Min Act: -0.0000

Data Index: 787539 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1078011 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1118833 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3458. Min Act: -0.0000

Data Index: 582405 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1751208 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1204119 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3142. Min Act: -0.0000

Data Index: 363800 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.5249. Min Range: -0.5249

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1547771 (The Pile)

Max Activating Token Index: 995