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

Dataset: The Pile

Neuron 2454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.2090. Min Act: -0.0000

Data Index: 194740 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1552384 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0813. Min Act: -0.0000

Data Index: 836855 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0982. Min Act: -0.0000

Data Index: 394480 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.1511. Min Act: -0.0000

Data Index: 683462 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1223747 (The Pile)

Max Activating Token Index: 289

Text #6

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0681. Min Act: -0.0000

Data Index: 353316 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1405701 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1328887 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1233078 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1848144 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1119840 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9556. Min Act: -0.0000

Data Index: 314947 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1744852 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1280312 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1490465 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9240. Min Act: -0.0000

Data Index: 510774 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9284. Min Act: -0.0000

Data Index: 586597 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9556. Min Act: -0.0000

Data Index: 852979 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1498088 (The Pile)

Max Activating Token Index: 773