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

Dataset: The Pile

Neuron 2480 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: 0.7702. Min Range: -0.7702

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1586309 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.7368. Min Act: -0.0000

Data Index: 570199 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1660056 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.7125. Min Act: 0.0000

Data Index: 999121 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1506352 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5911. Min Act: -0.0000

Data Index: 887556 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1441967 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5956. Min Act: -0.0000

Data Index: 344772 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1980360 (The Pile)

Max Activating Token Index: 636

Text #9

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1288545 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5819. Min Act: -0.0000

Data Index: 854254 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1862074 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1180242 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5626. Min Act: 0.0000

Data Index: 807771 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5011. Min Act: -0.0000

Data Index: 399663 (The Pile)

Max Activating Token Index: 849

Text #15

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1219495 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5295. Min Act: 0.0000

Data Index: 637470 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5287. Min Act: -0.0000

Data Index: 613160 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1934220 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.4565. Min Act: 0.0000

Data Index: 1232202 (The Pile)

Max Activating Token Index: 746