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

Dataset: The Pile

Neuron 2446 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.7845. Min Act: 0.0000

Data Index: 51986 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.6849. Min Act: 0.0000

Data Index: 571666 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.5698. Min Act: -0.0000

Data Index: 563826 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.5153. Min Act: 0.0000

Data Index: 1806986 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1989021 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3860. Min Act: 0.0000

Data Index: 1207700 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1933533 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1207685 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1846121 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3565. Min Act: 0.0000

Data Index: 219039 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.2449. Min Act: 0.0000

Data Index: 429102 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1589689 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3362. Min Act: -0.0000

Data Index: 157705 (The Pile)

Max Activating Token Index: 561

Text #13

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.2716. Min Act: 0.0000

Data Index: 1331421 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1676879 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1342966 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3360. Min Act: -0.0000

Data Index: 653587 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1419925 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1510392 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.7845. Min Range: -0.7845

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1647632 (The Pile)

Max Activating Token Index: 459