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

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

Neuron 365 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: 0.6524. Min Range: -0.6524

Max Act: 0.6524. Min Act: -0.0000

Data Index: 585660 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1052031 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6075. Min Act: -0.0000

Data Index: 822587 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5716. Min Act: -0.0000

Data Index: 868579 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5284. Min Act: -0.0000

Data Index: 493883 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1241428 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5131. Min Act: -0.0000

Data Index: 616647 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4916. Min Act: -0.0000

Data Index: 827301 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5064. Min Act: -0.0000

Data Index: 534819 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5048. Min Act: -0.0000

Data Index: 650367 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4857. Min Act: -0.0000

Data Index: 7107 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4983. Min Act: -0.0000

Data Index: 839378 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1327219 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5027. Min Act: -0.0000

Data Index: 572821 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4727. Min Act: -0.0000

Data Index: 972033 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4992. Min Act: -0.0000

Data Index: 119796 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1297455 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1248661 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1303311 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4634. Min Act: -0.0000

Data Index: 666865 (C4 (Web Text))

Max Activating Token Index: 527