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

Dataset: The Pile

Neuron 4627 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1185561 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1897291 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1228628 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6045. Min Act: -0.0000

Data Index: 692193 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1521441 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1853075 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1725048 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5924. Min Act: -0.0000

Data Index: 701760 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6182. Min Act: -0.0000

Data Index: 621042 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1593556 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1228327 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1120054 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1383480 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5586. Min Act: -0.0000

Data Index: 578544 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5860. Min Act: -0.0000

Data Index: 356014 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5406. Min Act: -0.0000

Data Index: 842258 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1747789 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1436978 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5693. Min Act: -0.0000

Data Index: 111475 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5543. Min Act: -0.0000

Data Index: 811822 (The Pile)

Max Activating Token Index: 370