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

Dataset: The Pile

Neuron 2639 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: 1.3425. Min Range: -1.3425

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1143953 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1802047 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2945. Min Act: -0.0000

Data Index: 162766 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2195. Min Act: -0.0000

Data Index: 1321393 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2595. Min Act: -0.0000

Data Index: 796746 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2389. Min Act: -0.0000

Data Index: 662325 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1858. Min Act: -0.0000

Data Index: 669385 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2132. Min Act: -0.0000

Data Index: 800166 (The Pile)

Max Activating Token Index: 432

Text #8

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1497 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2272. Min Act: -0.0000

Data Index: 956288 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1361022 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1773729 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.2063. Min Act: -0.0000

Data Index: 1980580 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1259. Min Act: -0.0000

Data Index: 350824 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1730241 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1707292 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1041. Min Act: -0.0000

Data Index: 870713 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1041128 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1000. Min Act: -0.0000

Data Index: 810235 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.3425. Min Range: -1.3425

Max Act: 1.1146. Min Act: -0.0000

Data Index: 825533 (The Pile)

Max Activating Token Index: 502