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

Dataset: The Pile

Neuron 1896 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: 3.4103. Min Range: -3.4103

Max Act: 3.4103. Min Act: -0.0000

Data Index: 704818 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.3814. Min Act: -0.0000

Data Index: 1856018 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.1080. Min Act: -0.0000

Data Index: 657614 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.3851. Min Act: -0.0000

Data Index: 1179775 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.0666. Min Act: -0.0000

Data Index: 1267672 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.3565. Min Act: -0.0000

Data Index: 1687078 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.0765. Min Act: -0.0000

Data Index: 1488257 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.8247. Min Act: -0.0000

Data Index: 619394 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.0744. Min Act: -0.0000

Data Index: 1509799 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.0347. Min Act: -0.0000

Data Index: 1824309 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.3533. Min Act: -0.0000

Data Index: 526095 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.1458. Min Act: -0.0000

Data Index: 1665548 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.6819. Min Act: -0.0000

Data Index: 1312378 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.9597. Min Act: -0.0000

Data Index: 1547038 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.7364. Min Act: -0.0000

Data Index: 811290 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.7175. Min Act: -0.0000

Data Index: 1761228 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.8119. Min Act: -0.0000

Data Index: 1861989 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.5422. Min Act: -0.0000

Data Index: 1326348 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.7777. Min Act: -0.0000

Data Index: 890899 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 3.4103. Min Range: -3.4103

Max Act: 2.4746. Min Act: -0.0000

Data Index: 1959330 (The Pile)

Max Activating Token Index: 857