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

Dataset: The Pile

Neuron 2879 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.6383. Min Act: -0.0000

Data Index: 530127 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5354. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1909916 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5086. Min Act: -0.0000

Data Index: 598881 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5107. Min Act: -0.0000

Data Index: 13979 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5620. Min Act: -0.0000

Data Index: 630430 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1269625 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1940056 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4800. Min Act: -0.0000

Data Index: 521958 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1312688 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1995183 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1877748 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4997. Min Act: -0.0000

Data Index: 375987 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1279265 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1610394 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1828516 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4539. Min Act: -0.0000

Data Index: 545444 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4691. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4508. Min Act: -0.0000

Data Index: 646940 (The Pile)

Max Activating Token Index: 955