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

Dataset: The Pile

Neuron 1644 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: 0.5900. Min Range: -0.5900

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1115766 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5278. Min Act: -0.0000

Data Index: 988662 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5486. Min Act: -0.0000

Data Index: 416617 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1474484 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4985. Min Act: -0.0000

Data Index: 896135 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5900. Min Act: -0.0000

Data Index: 801287 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4965. Min Act: -0.0000

Data Index: 835305 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1589677 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4751. Min Act: -0.0000

Data Index: 168307 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1540216 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1182838 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1159099 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3849. Min Act: -0.0000

Data Index: 407169 (The Pile)

Max Activating Token Index: 556

Text #13

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3525. Min Act: -0.0000

Data Index: 499137 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3636. Min Act: -0.0000

Data Index: 34150 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1883225 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3385. Min Act: -0.0000

Data Index: 891804 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3350. Min Act: -0.0000

Data Index: 266061 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3283. Min Act: -0.0000

Data Index: 887462 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.3480. Min Act: -0.0000

Data Index: 198431 (The Pile)

Max Activating Token Index: 305