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

Dataset: The Pile

Neuron 2049 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: 0.8401. Min Range: -0.8401

Max Act: 0.8401. Min Act: -0.0000

Data Index: 738031 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1599997 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1069314 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6688. Min Act: -0.0000

Data Index: 363241 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1813028 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1084669 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1497073 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1581227 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1692594 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6492. Min Act: -0.0000

Data Index: 48877 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6515. Min Act: -0.0000

Data Index: 811175 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6537. Min Act: -0.0000

Data Index: 649199 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6391. Min Act: -0.0000

Data Index: 362308 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6394. Min Act: -0.0000

Data Index: 217600 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1777187 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6562. Min Act: -0.0000

Data Index: 843463 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1292355 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6720. Min Act: -0.0000

Data Index: 24698 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1569148 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5904. Min Act: -0.0000

Data Index: 69794 (The Pile)

Max Activating Token Index: 851