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

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

Neuron 1769 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.8384. Min Range: -10.8384

Max Act: 10.8384. Min Act: -0.0000

Data Index: 79041 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 10.8384. Min Range: -10.8384

Max Act: 10.8218. Min Act: -0.0000

Data Index: 1416657 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 10.8384. Min Range: -10.8384

Max Act: 10.3722. Min Act: -0.0000

Data Index: 389582 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 10.8384. Min Range: -10.8384

Max Act: 10.3896. Min Act: -0.0000

Data Index: 433897 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.8736. Min Act: -0.0000

Data Index: 507210 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.8772. Min Act: -0.0000

Data Index: 1338870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.9479. Min Act: -0.0000

Data Index: 687678 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.9429. Min Act: -0.0000

Data Index: 1359520 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.1384. Min Act: -0.0000

Data Index: 624616 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.9789. Min Act: -0.0000

Data Index: 166579 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.3542. Min Act: -0.0000

Data Index: 573720 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.1072. Min Act: -0.0000

Data Index: 832405 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.9444. Min Act: -0.0000

Data Index: 767129 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.9691. Min Act: -0.0000

Data Index: 833606 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.9706. Min Act: -0.0000

Data Index: 225125 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 10.8384. Min Range: -10.8384

Max Act: 9.1988. Min Act: -0.0000

Data Index: 1608311 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.9761. Min Act: -0.0000

Data Index: 1463830 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.8301. Min Act: -0.0000

Data Index: 463595 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.5081. Min Act: -0.0000

Data Index: 1457621 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 10.8384. Min Range: -10.8384

Max Act: 8.7815. Min Act: -0.0000

Data Index: 1131215 (C4 (Web Text))

Max Activating Token Index: 977