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

Dataset: The Pile

Neuron 1481 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6592. Min Act: -0.0000

Data Index: 586587 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6549. Min Act: -0.0000

Data Index: 658044 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5630. Min Act: -0.0000

Data Index: 500371 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1198057 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5323. Min Act: -0.0000

Data Index: 579912 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1223752 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1811007 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1861888 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5061. Min Act: -0.0000

Data Index: 898837 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4962. Min Act: -0.0000

Data Index: 108769 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1167862 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1794594 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4795. Min Act: -0.0000

Data Index: 628252 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1423209 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1189972 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1401714 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4695. Min Act: -0.0000

Data Index: 150707 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4803. Min Act: -0.0000

Data Index: 334053 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4576. Min Act: -0.0000

Data Index: 852255 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4547. Min Act: -0.0000

Data Index: 526626 (The Pile)

Max Activating Token Index: 719