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

Dataset: The Pile

Neuron 1820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9402. Min Act: -0.0000

Data Index: 771134 (The Pile)

Max Activating Token Index: 741

Text #1

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8041. Min Act: -0.0000

Data Index: 232755 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1643484 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8258. Min Act: -0.0000

Data Index: 989507 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1171865 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1863934 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1050230 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1828042 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7924. Min Act: -0.0000

Data Index: 650768 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1111892 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7877. Min Act: -0.0000

Data Index: 50667 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7087. Min Act: -0.0000

Data Index: 157311 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6787. Min Act: -0.0000

Data Index: 206980 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7325. Min Act: -0.0000

Data Index: 795462 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1286513 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1341763 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1368951 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5847. Min Act: -0.0000

Data Index: 586389 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1528863 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6508. Min Act: -0.0000

Data Index: 527169 (The Pile)

Max Activating Token Index: 142