Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7845. Min Act: -0.0000

Data Index: 329537 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7436. Min Act: -0.0000

Data Index: 122394 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1220069 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7540. Min Act: -0.0000

Data Index: 451416 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6851. Min Act: -0.0000

Data Index: 555053 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6504. Min Act: -0.0000

Data Index: 521962 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6570. Min Act: -0.0000

Data Index: 120110 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1097837 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1152084 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6351. Min Act: -0.0000

Data Index: 719881 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.7443. Min Act: -0.0000

Data Index: 141722 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1223569 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6357. Min Act: -0.0001

Data Index: 827100 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1035718 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6515. Min Act: -0.0001

Data Index: 491348 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6507. Min Act: -0.0001

Data Index: 307611 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6651. Min Act: -0.0000

Data Index: 146138 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1198584 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.5666. Min Act: -0.0000

Data Index: 489939 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.8063. Min Range: -0.8063

Max Act: 0.6024. Min Act: -0.0000

Data Index: 481806 (C4 (Web Text))

Max Activating Token Index: 464