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

Dataset: The Pile

Neuron 3405 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1455984 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1661609 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.4446. Min Act: -0.0000

Data Index: 546632 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1378186 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2788. Min Act: -0.0000

Data Index: 322058 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1158190 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.2472. Min Act: -0.0000

Data Index: 977243 (The Pile)

Max Activating Token Index: 689

Text #7

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1774303 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1785. Min Act: -0.0000

Data Index: 808282 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1527347 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1963. Min Act: -0.0000

Data Index: 865658 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 1.5353. Min Range: -1.5353

Max Act: 0.9921. Min Act: -0.0000

Data Index: 686279 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1815146 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1276639 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1881952 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1223877 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1732165 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1406785 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 1.5353. Min Range: -1.5353

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1603436 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 1.5353. Min Range: -1.5353

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1586764 (The Pile)

Max Activating Token Index: 185