Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 126 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7937. Min Act: -0.0000

Data Index: 739082 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7368. Min Act: -0.0000

Data Index: 12668 (The Pile)

Max Activating Token Index: 917

Text #2

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7429. Min Act: -0.0000

Data Index: 301382 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7305. Min Act: -0.0000

Data Index: 959809 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6671. Min Act: -0.0000

Data Index: 871677 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1561389 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7920. Min Act: -0.0000

Data Index: 578727 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7195. Min Act: -0.0000

Data Index: 784195 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1925711 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1688938 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1542502 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.7285. Min Act: -0.0000

Data Index: 568002 (The Pile)

Max Activating Token Index: 940

Text #12

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1978584 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6230. Min Act: -0.0000

Data Index: 732674 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1739542 (The Pile)

Max Activating Token Index: 520

Text #15

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6124. Min Act: -0.0000

Data Index: 43161 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5607. Min Act: -0.0000

Data Index: 555397 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1813190 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.5825. Min Act: -0.0000

Data Index: 965144 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 0.8335. Min Range: -0.8335

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1909169 (The Pile)

Max Activating Token Index: 827