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

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

Neuron 3680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1185976 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1019011 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0190. Min Act: -0.0000

Data Index: 858010 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 1.0923. Min Range: -1.0923

Max Act: 1.0167. Min Act: -0.0000

Data Index: 23090 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9472. Min Act: -0.0000

Data Index: 698648 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1042796 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9470. Min Act: -0.0000

Data Index: 362552 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1153977 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1199138 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1205568 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1336165 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.9230. Min Act: -0.0000

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1037226 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8902. Min Act: -0.0000

Data Index: 11675 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8668. Min Act: -0.0000

Data Index: 864019 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1178227 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1224627 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8575. Min Act: -0.0000

Data Index: 627227 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.7994. Min Act: -0.0000

Data Index: 481177 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 1.0923. Min Range: -1.0923

Max Act: 0.8149. Min Act: -0.0000

Data Index: 304904 (C4 (Web Text))

Max Activating Token Index: 847