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

Dataset: The Pile

Neuron 3817 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: 1.0122. Min Range: -1.0122

Max Act: 1.0122. Min Act: -0.0000

Data Index: 424232 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.9222. Min Act: -0.0000

Data Index: 547223 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.8646. Min Act: -0.0000

Data Index: 222897 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.8893. Min Act: -0.0000

Data Index: 447026 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.8021. Min Act: -0.0000

Data Index: 445043 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7927. Min Act: -0.0000

Data Index: 195361 (The Pile)

Max Activating Token Index: 225

Text #6

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1211605 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7786. Min Act: -0.0000

Data Index: 87444 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1282316 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7444. Min Act: -0.0000

Data Index: 518636 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7572. Min Act: -0.0000

Data Index: 158952 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7064. Min Act: -0.0000

Data Index: 800052 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1888476 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1197846 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6560. Min Act: -0.0000

Data Index: 201621 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6912. Min Act: -0.0000

Data Index: 797451 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1513868 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6485. Min Act: -0.0000

Data Index: 760344 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1360171 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.0122. Min Range: -1.0122

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1700120 (The Pile)

Max Activating Token Index: 412