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

Dataset: The Pile

Neuron 3516 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.9465. Min Act: -0.0000

Data Index: 374134 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1519482 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1501991 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.8371. Min Act: -0.0000

Data Index: 185695 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1109659 (The Pile)

Max Activating Token Index: 155

Text #5

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1068503 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1549256 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1721082 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1173250 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7297. Min Act: -0.0000

Data Index: 887743 (The Pile)

Max Activating Token Index: 504

Text #10

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1364818 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7496. Min Act: -0.0000

Data Index: 300630 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1997714 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.7266. Min Act: -0.0000

Data Index: 568324 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1224567 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1926906 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6908. Min Act: -0.0000

Data Index: 576748 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6562. Min Act: -0.0000

Data Index: 598113 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6568. Min Act: -0.0000

Data Index: 694652 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 0.9465. Min Range: -0.9465

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1690283 (The Pile)

Max Activating Token Index: 31