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

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

Neuron 5599 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0354. Min Range: -1.0354

Max Act: 1.0354. Min Act: -0.0000

Data Index: 464316 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9896. Min Act: -0.0000

Data Index: 711882 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9314. Min Act: 0.0001

Data Index: 982960 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8408. Min Act: 0.0000

Data Index: 338092 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8770. Min Act: -0.0000

Data Index: 319309 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8684. Min Act: -0.0000

Data Index: 440966 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1060709 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8543. Min Act: -0.0000

Data Index: 680916 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8556. Min Act: 0.0000

Data Index: 812298 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8413. Min Act: -0.0000

Data Index: 920819 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1203649 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7984. Min Act: -0.0000

Data Index: 991005 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7699. Min Act: 0.0000

Data Index: 1113530 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7463. Min Act: -0.0000

Data Index: 91013 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7455. Min Act: 0.0000

Data Index: 1267117 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7228. Min Act: -0.0000

Data Index: 71560 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7883. Min Act: -0.0000

Data Index: 332464 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7365. Min Act: 0.0000

Data Index: 1062753 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7435. Min Act: 0.0000

Data Index: 51113 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7404. Min Act: -0.0000

Data Index: 734907 (C4 (Web Text))

Max Activating Token Index: 79