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

Dataset: The Pile

Neuron 3130 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.8256. Min Act: -0.0000

Data Index: 809487 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1660547 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5912. Min Act: -0.0000

Data Index: 349600 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1286204 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1138113 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1902570 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5307. Min Act: -0.0000

Data Index: 373540 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1381577 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5378. Min Act: -0.0000

Data Index: 807770 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5377. Min Act: -0.0000

Data Index: 932554 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5529. Min Act: -0.0000

Data Index: 740067 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1842129 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5145. Min Act: -0.0000

Data Index: 682725 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.5081. Min Act: -0.0000

Data Index: 456683 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1214910 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4862. Min Act: -0.0000

Data Index: 49478 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1759160 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4358. Min Act: -0.0000

Data Index: 143481 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1353186 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.8256. Min Range: -0.8256

Max Act: 0.4615. Min Act: -0.0000

Data Index: 267160 (The Pile)

Max Activating Token Index: 45