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

Dataset: The Pile

Neuron 2679 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.4371. Min Act: -0.0000

Data Index: 886401 (The Pile)

Max Activating Token Index: 951

Text #1

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3917. Min Act: -0.0000

Data Index: 864901 (The Pile)

Max Activating Token Index: 893

Text #2

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3904. Min Act: -0.0000

Data Index: 276362 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1685567 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1959313 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3873. Min Act: -0.0000

Data Index: 640762 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3771. Min Act: -0.0000

Data Index: 81002 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3690. Min Act: -0.0000

Data Index: 669403 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3742. Min Act: -0.0000

Data Index: 853492 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3713. Min Act: -0.0000

Data Index: 950187 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1876151 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3807. Min Act: -0.0000

Data Index: 560161 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3777. Min Act: -0.0000

Data Index: 691369 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3629. Min Act: -0.0000

Data Index: 235208 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1410531 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1302895 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1380492 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3627. Min Act: -0.0000

Data Index: 318912 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1936162 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.4371. Min Range: -0.4371

Max Act: 0.3493. Min Act: -0.0000

Data Index: 415966 (The Pile)

Max Activating Token Index: 531