Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1595 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1173. Min Act: -0.0002

Data Index: 180555 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1092. Min Act: -0.0002

Data Index: 435134 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0982. Min Act: -0.0002

Data Index: 246860 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0970. Min Act: -0.0001

Data Index: 259764 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0999. Min Act: -0.0001

Data Index: 617381 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0882. Min Act: -0.0001

Data Index: 981882 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1534669 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0918. Min Act: -0.0001

Data Index: 569228 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0842. Min Act: -0.0001

Data Index: 288902 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0843. Min Act: -0.0002

Data Index: 725420 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0831. Min Act: -0.0002

Data Index: 491773 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0861. Min Act: -0.0002

Data Index: 69309 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0825. Min Act: -0.0001

Data Index: 724361 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0848. Min Act: -0.0002

Data Index: 279926 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0839. Min Act: -0.0002

Data Index: 465215 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0833. Min Act: -0.0001

Data Index: 355199 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1321530 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1214589 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0775. Min Act: -0.0001

Data Index: 661134 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0783. Min Act: -0.0002

Data Index: 567373 (C4 (Web Text))

Max Activating Token Index: 258