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

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

Neuron 4307 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.5063. Min Act: -0.0000

Data Index: 237793 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2225. Min Act: -0.0000

Data Index: 363184 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2632. Min Act: -0.0000

Data Index: 379676 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2455. Min Act: -0.0000

Data Index: 328736 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2251. Min Act: -0.0000

Data Index: 470300 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2377. Min Act: -0.0000

Data Index: 876962 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1067823 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0785. Min Act: -0.0000

Data Index: 105874 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.1901. Min Act: -0.0000

Data Index: 582609 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.5063. Min Range: -1.5063

Max Act: 0.9835. Min Act: -0.0000

Data Index: 168292 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.1427. Min Act: -0.0000

Data Index: 593938 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0754. Min Act: -0.0000

Data Index: 479673 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.1507. Min Act: -0.0000

Data Index: 803539 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0095. Min Act: -0.0000

Data Index: 602593 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 1.5063. Min Range: -1.5063

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 1.5063. Min Range: -1.5063

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1144433 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1567588 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 1.5063. Min Range: -1.5063

Max Act: 0.9950. Min Act: -0.0000

Data Index: 759574 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.5063. Min Range: -1.5063

Max Act: 0.9644. Min Act: -0.0000

Data Index: 930997 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.5063. Min Range: -1.5063

Max Act: 1.0269. Min Act: -0.0000

Data Index: 115111 (C4 (Web Text))

Max Activating Token Index: 381