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

Dataset: The Pile

Neuron 2852 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: 1.8330. Min Range: -1.8330

Max Act: 1.8330. Min Act: -0.0000

Data Index: 1889338 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.4719. Min Act: -0.0000

Data Index: 1614877 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.3281. Min Act: -0.0000

Data Index: 8771 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.3567. Min Act: -0.0000

Data Index: 672902 (The Pile)

Max Activating Token Index: 470

Text #4

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.2512. Min Act: -0.0000

Data Index: 863797 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1936633 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.2139. Min Act: -0.0000

Data Index: 1459807 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.2333. Min Act: -0.0000

Data Index: 518411 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.1682. Min Act: -0.0000

Data Index: 807021 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1108275 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1004661 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1764116 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1345951 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.1088. Min Act: -0.0000

Data Index: 705480 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1943002 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 1.8330. Min Range: -1.8330

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1519948 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.1559. Min Act: -0.0000

Data Index: 1473559 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.0748. Min Act: -0.0000

Data Index: 173643 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.0662. Min Act: -0.0000

Data Index: 4820 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 1.8330. Min Range: -1.8330

Max Act: 1.0062. Min Act: -0.0000

Data Index: 202900 (The Pile)

Max Activating Token Index: 1015