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

Dataset: The Pile

Neuron 2586 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: 1.3846. Min Range: -1.3846

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1669394 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1645599 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1212656 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1957283 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0170. Min Act: -0.0000

Data Index: 952864 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0551. Min Act: -0.0000

Data Index: 333735 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1949040 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1757891 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9511. Min Act: -0.0000

Data Index: 522240 (The Pile)

Max Activating Token Index: 797

Text #9

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0098. Min Act: -0.0000

Data Index: 492524 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0447. Min Act: -0.0000

Data Index: 692783 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.7899. Min Act: -0.0000

Data Index: 91233 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1471909 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1304139 (The Pile)

Max Activating Token Index: 568

Text #14

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1442962 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1543561 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 1.3846. Min Range: -1.3846

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1902895 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1236489 (The Pile)

Max Activating Token Index: 579

Text #18

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.9166. Min Act: -0.0000

Data Index: 82151 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.3846. Min Range: -1.3846

Max Act: 0.6900. Min Act: -0.0000

Data Index: 441984 (The Pile)

Max Activating Token Index: 687