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

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

Neuron 2697 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0001

Data Index: 943559 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0985. Min Act: -0.0001

Data Index: 129243 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0887. Min Act: -0.0001

Data Index: 602234 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0940. Min Act: -0.0001

Data Index: 816344 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0870. Min Act: -0.0001

Data Index: 836322 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0857. Min Act: -0.0001

Data Index: 436964 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0851. Min Act: -0.0001

Data Index: 188557 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1159282 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0841. Min Act: -0.0001

Data Index: 235985 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0774. Min Act: -0.0001

Data Index: 857290 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0804. Min Act: -0.0001

Data Index: 743055 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0771. Min Act: -0.0001

Data Index: 800708 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0825. Min Act: -0.0001

Data Index: 819807 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0818. Min Act: -0.0001

Data Index: 789347 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0789. Min Act: -0.0001

Data Index: 266144 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0780. Min Act: -0.0001

Data Index: 603143 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0770. Min Act: -0.0001

Data Index: 280665 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0671. Min Act: -0.0001

Data Index: 26169 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0771. Min Act: -0.0001

Data Index: 131012 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0748. Min Act: -0.0001

Data Index: 311734 (C4 (Web Text))

Max Activating Token Index: 357