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

Dataset: The Pile

Neuron 2542 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.7680. Min Act: -0.0000

Data Index: 712092 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.4290. Min Act: -0.0000

Data Index: 532435 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.3880. Min Act: -0.0000

Data Index: 1106304 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.3714. Min Act: -0.0000

Data Index: 666745 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.2826. Min Act: -0.0000

Data Index: 636045 (The Pile)

Max Activating Token Index: 47

Text #5

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.4052. Min Act: -0.0000

Data Index: 1818838 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.7938. Min Act: -0.0000

Data Index: 1353372 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.4118. Min Act: -0.0000

Data Index: 207310 (The Pile)

Max Activating Token Index: 853

Text #8

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.2161. Min Act: -0.0000

Data Index: 1553571 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.5197. Min Act: -0.0000

Data Index: 1762238 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.2501. Min Act: -0.0000

Data Index: 545108 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.4364. Min Act: -0.0000

Data Index: 551100 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.4509. Min Act: -0.0000

Data Index: 1988880 (The Pile)

Max Activating Token Index: 922

Text #13

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.0254. Min Act: -0.0000

Data Index: 1955231 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.1533. Min Act: -0.0000

Data Index: 1404292 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.2092. Min Act: -0.0000

Data Index: 1572728 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.1594. Min Act: -0.0000

Data Index: 996911 (The Pile)

Max Activating Token Index: 669

Text #17

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.2681. Min Act: -0.0000

Data Index: 1111640 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 5.7938. Min Range: -5.7938

Max Act: 4.9643. Min Act: -0.0000

Data Index: 1234690 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 5.7938. Min Range: -5.7938

Max Act: 5.1487. Min Act: -0.0000

Data Index: 1988562 (The Pile)

Max Activating Token Index: 82