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

Dataset: The Pile

Neuron 3409 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1600685 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1201937 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1997317 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1071055 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1772428 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3667. Min Act: -0.0000

Data Index: 864712 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3540. Min Act: -0.0000

Data Index: 559562 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3865. Min Act: -0.0000

Data Index: 17453 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1325507 (The Pile)

Max Activating Token Index: 772

Text #9

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3536. Min Act: -0.0000

Data Index: 192234 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3639. Min Act: -0.0000

Data Index: 923685 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3554. Min Act: -0.0000

Data Index: 334444 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1056705 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3404. Min Act: -0.0000

Data Index: 260628 (The Pile)

Max Activating Token Index: 360

Text #14

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1499386 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3573. Min Act: -0.0000

Data Index: 846902 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3039. Min Act: -0.0000

Data Index: 695647 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1301743 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3192. Min Act: -0.0000

Data Index: 549410 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3474. Min Act: -0.0000

Data Index: 564520 (The Pile)

Max Activating Token Index: 238