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

Dataset: The Pile

Neuron 872 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: 0.3550. Min Range: -0.3550

Max Act: 0.3235. Min Act: -0.0000

Data Index: 305523 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3296. Min Act: -0.0000

Data Index: 697417 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1943651 (The Pile)

Max Activating Token Index: 340

Text #3

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1168702 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1979402 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3188. Min Act: -0.0000

Data Index: 477819 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3058. Min Act: -0.0000

Data Index: 810839 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2762. Min Act: -0.0000

Data Index: 777667 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2465. Min Act: -0.0000

Data Index: 894912 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2897. Min Act: -0.0000

Data Index: 900200 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2281. Min Act: -0.0000

Data Index: 786363 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2804. Min Act: -0.0000

Data Index: 655302 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2934. Min Act: -0.0000

Data Index: 273146 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1791949 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2452. Min Act: -0.0000

Data Index: 198172 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2374. Min Act: -0.0000

Data Index: 525945 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1760197 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2597. Min Act: -0.0000

Data Index: 397036 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1169545 (The Pile)

Max Activating Token Index: 734

Text #19

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1027920 (The Pile)

Max Activating Token Index: 443