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

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

Neuron 876 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1025. Min Range: -1.1025

Max Act: 1.1025. Min Act: -0.0000

Data Index: 131547 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.1025. Min Range: -1.1025

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1267131 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 1.1025. Min Range: -1.1025

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1155009 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9969. Min Act: -0.0000

Data Index: 88063 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9864. Min Act: -0.0000

Data Index: 398423 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1038993 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9758. Min Act: -0.0000

Data Index: 38684 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9290. Min Act: -0.0000

Data Index: 578302 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9654. Min Act: -0.0000

Data Index: 65034 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1221605 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9510. Min Act: -0.0000

Data Index: 58899 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1220194 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9617. Min Act: -0.0000

Data Index: 982970 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8523. Min Act: -0.0000

Data Index: 570852 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8710. Min Act: -0.0000

Data Index: 560300 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8480. Min Act: -0.0000

Data Index: 134302 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8384. Min Act: -0.0000

Data Index: 90327 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8525. Min Act: -0.0000

Data Index: 320152 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1359730 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8418. Min Act: -0.0000

Data Index: 605509 (C4 (Web Text))

Max Activating Token Index: 905