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

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

Neuron 4001 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1322877 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1052874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1253182 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1016070 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.4094. Min Act: -0.0000

Data Index: 758280 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1194208 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1004252 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3867. Min Act: -0.0000

Data Index: 838604 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3847. Min Act: -0.0000

Data Index: 186195 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3947. Min Act: -0.0000

Data Index: 342642 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3692. Min Act: -0.0000

Data Index: 817837 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1188200 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3744. Min Act: -0.0000

Data Index: 51920 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3600. Min Act: -0.0000

Data Index: 421426 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3509. Min Act: -0.0000

Data Index: 341709 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3587. Min Act: -0.0000

Data Index: 763607 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3581. Min Act: -0.0000

Data Index: 477415 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1060063 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1242296 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.4770. Min Range: -0.4770

Max Act: 0.3495. Min Act: -0.0000

Data Index: 983541 (C4 (Web Text))

Max Activating Token Index: 569