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

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

Neuron 4651 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.8861. Min Act: -0.0002

Data Index: 1222421 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.7912. Min Act: -0.0002

Data Index: 342004 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.8122. Min Act: -0.0002

Data Index: 1155969 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.8154. Min Act: -0.0002

Data Index: 843742 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.8927. Min Act: -0.0002

Data Index: 1251700 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.8304. Min Act: -0.0002

Data Index: 398784 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.8893. Min Act: -0.0002

Data Index: 782587 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.7972. Min Act: -0.0002

Data Index: 533130 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.8264. Min Act: -0.0002

Data Index: 1076799 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.7743. Min Act: -0.0002

Data Index: 1337296 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.7553. Min Act: -0.0002

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.7340. Min Act: -0.0002

Data Index: 74559 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.6525. Min Act: -0.0002

Data Index: 153596 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.6375. Min Act: -0.0002

Data Index: 1121870 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.6312. Min Act: -0.0002

Data Index: 519999 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.6222. Min Act: -0.0002

Data Index: 361417 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.5453. Min Act: -0.0002

Data Index: 540803 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.5260. Min Act: -0.0002

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.4845. Min Act: -0.0002

Data Index: 298993 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.8927. Min Range: -1.8927

Max Act: 1.4593. Min Act: -0.0002

Data Index: 111186 (C4 (Web Text))

Max Activating Token Index: 745