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

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

Neuron 1028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.5829. Min Act: -0.0000

Data Index: 935586 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.5893. Min Act: -0.0000

Data Index: 450354 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.5745. Min Act: -0.0000

Data Index: 1036353 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.5237. Min Act: -0.0000

Data Index: 820754 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.6062. Min Act: -0.0000

Data Index: 820587 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.5918. Min Act: -0.0000

Data Index: 809486 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.4876. Min Act: -0.0000

Data Index: 500594 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.4492. Min Act: -0.0000

Data Index: 158969 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.4447. Min Act: -0.0000

Data Index: 13023 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.4771. Min Act: -0.0000

Data Index: 1201674 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.4193. Min Act: -0.0000

Data Index: 467582 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1175414 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3950. Min Act: -0.0000

Data Index: 1159384 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.4135. Min Act: -0.0000

Data Index: 603956 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1251358 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3530. Min Act: -0.0000

Data Index: 1276269 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3312. Min Act: -0.0000

Data Index: 629538 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1352058 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3269. Min Act: -0.0000

Data Index: 952268 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.6062. Min Range: -1.6062

Max Act: 1.3109. Min Act: -0.0000

Data Index: 68612 (C4 (Web Text))

Max Activating Token Index: 647