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

Dataset: The Pile

Neuron 3073 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5813. Min Act: -0.0001

Data Index: 783688 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1008093 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1217983 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3408. Min Act: -0.0000

Data Index: 61659 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3793. Min Act: -0.0000

Data Index: 660800 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3684. Min Act: -0.0000

Data Index: 606708 (The Pile)

Max Activating Token Index: 811

Text #6

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3416. Min Act: -0.0000

Data Index: 180522 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3109. Min Act: -0.0000

Data Index: 128423 (The Pile)

Max Activating Token Index: 744

Text #8

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3387. Min Act: -0.0000

Data Index: 1627778 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1457756 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1182776 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3213. Min Act: -0.0000

Data Index: 512100 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1759313 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3017. Min Act: -0.0000

Data Index: 717561 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3051. Min Act: -0.0000

Data Index: 438836 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1928249 (The Pile)

Max Activating Token Index: 220

Text #16

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1687565 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.2840. Min Act: -0.0000

Data Index: 528101 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.2967. Min Act: -0.0000

Data Index: 363222 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.2835. Min Act: -0.0000

Data Index: 148337 (The Pile)

Max Activating Token Index: 454