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

Dataset: The Pile

Neuron 2116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.9037. Min Act: -0.0000

Data Index: 634673 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7817. Min Act: -0.0000

Data Index: 923977 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8636. Min Act: 0.0000

Data Index: 330826 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7943. Min Act: -0.0000

Data Index: 286368 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7940. Min Act: -0.0000

Data Index: 853642 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1204418 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7554. Min Act: -0.0000

Data Index: 209410 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7479. Min Act: -0.0000

Data Index: 350056 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7008. Min Act: -0.0000

Data Index: 872840 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1093782 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6979. Min Act: -0.0000

Data Index: 20526 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7925. Min Act: -0.0000

Data Index: 506143 (The Pile)

Max Activating Token Index: 972

Text #12

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7136. Min Act: -0.0000

Data Index: 639719 (The Pile)

Max Activating Token Index: 913

Text #13

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1262547 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1078106 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6552. Min Act: -0.0000

Data Index: 36457 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6902. Min Act: -0.0000

Data Index: 39521 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1909538 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1792976 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1777464 (The Pile)

Max Activating Token Index: 341