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

Dataset: The Pile

Neuron 3859 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1205911 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1663347 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1254807 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1355652 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1175468 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.2385. Min Act: -0.0000

Data Index: 309211 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1399420 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1889880 (The Pile)

Max Activating Token Index: 361

Text #8

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.8619. Min Act: -0.0000

Data Index: 250753 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 1.3696. Min Range: -1.3696

Max Act: 1.2249. Min Act: -0.0000

Data Index: 235182 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.9933. Min Act: -0.0000

Data Index: 232300 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1214402 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1078396 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1299420 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.9889. Min Act: -0.0000

Data Index: 688528 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.9134. Min Act: -0.0000

Data Index: 442579 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.8233. Min Act: -0.0000

Data Index: 895872 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.8392. Min Act: -0.0000

Data Index: 557345 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.7522. Min Act: -0.0000

Data Index: 120834 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 1.3696. Min Range: -1.3696

Max Act: 0.8664. Min Act: -0.0000

Data Index: 939001 (The Pile)

Max Activating Token Index: 518