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

Dataset: The Pile

Neuron 908 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1679361 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6133. Min Act: -0.0000

Data Index: 935503 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6584. Min Act: -0.0000

Data Index: 36862 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1674279 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1890066 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1960023 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1159582 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5849. Min Act: -0.0000

Data Index: 943393 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1767887 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5647. Min Act: -0.0000

Data Index: 886459 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1920613 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1406155 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1070181 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1228447 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5195. Min Act: -0.0000

Data Index: 723447 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1853522 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1831780 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1823121 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4758. Min Act: -0.0000

Data Index: 136476 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 0.6584. Min Range: -0.6584

Max Act: 0.4584. Min Act: -0.0000

Data Index: 319388 (The Pile)

Max Activating Token Index: 608