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

Dataset: The Pile

Neuron 214 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: 7.3463. Min Range: -7.3463

Max Act: 7.3463. Min Act: -0.0000

Data Index: 1793234 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 7.3463. Min Range: -7.3463

Max Act: 5.4905. Min Act: -0.0000

Data Index: 1560115 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 7.3463. Min Range: -7.3463

Max Act: 5.5947. Min Act: -0.0000

Data Index: 1913479 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 7.3463. Min Range: -7.3463

Max Act: 5.0814. Min Act: -0.0000

Data Index: 1366095 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 7.3463. Min Range: -7.3463

Max Act: 6.1249. Min Act: -0.0000

Data Index: 1271354 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 7.3463. Min Range: -7.3463

Max Act: 4.2720. Min Act: -0.0000

Data Index: 308474 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 7.3463. Min Range: -7.3463

Max Act: 4.0733. Min Act: -0.0000

Data Index: 1390004 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.6841. Min Act: -0.0000

Data Index: 817060 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.3295. Min Act: -0.0000

Data Index: 876062 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 7.3463. Min Range: -7.3463

Max Act: 4.1812. Min Act: -0.0000

Data Index: 1110352 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.9648. Min Act: -0.0000

Data Index: 269446 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.4309. Min Act: -0.0000

Data Index: 729276 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.9085. Min Act: -0.0000

Data Index: 874248 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.5359. Min Act: -0.0000

Data Index: 443350 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.6871. Min Act: -0.0000

Data Index: 1910187 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 7.3463. Min Range: -7.3463

Max Act: 4.8184. Min Act: -0.0000

Data Index: 1296875 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.6943. Min Act: -0.0000

Data Index: 201723 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.4840. Min Act: -0.0000

Data Index: 1600510 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 7.3463. Min Range: -7.3463

Max Act: 2.6840. Min Act: -0.0000

Data Index: 249653 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 7.3463. Min Range: -7.3463

Max Act: 3.0864. Min Act: -0.0000

Data Index: 1345197 (The Pile)

Max Activating Token Index: 314