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

Dataset: The Pile

Neuron 3282 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: 1.3131. Min Range: -1.3131

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1553421 (The Pile)

Max Activating Token Index: 371

Text #1

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1429749 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1414544 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9847. Min Act: -0.0000

Data Index: 487709 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1564087 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.0044. Min Act: -0.0000

Data Index: 335491 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1619128 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9044. Min Act: -0.0000

Data Index: 971242 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1589097 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9712. Min Act: -0.0000

Data Index: 768517 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 1.3131. Min Range: -1.3131

Max Act: 1.0232. Min Act: -0.0000

Data Index: 531395 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1594958 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1087262 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1019089 (The Pile)

Max Activating Token Index: 87

Text #14

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8895. Min Act: -0.0000

Data Index: 134976 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9907. Min Act: -0.0000

Data Index: 799775 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9167. Min Act: -0.0000

Data Index: 457993 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1739612 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1785545 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 1.3131. Min Range: -1.3131

Max Act: 0.9047. Min Act: -0.0000

Data Index: 878671 (The Pile)

Max Activating Token Index: 997