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

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

Neuron 574 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0678. Min Range: -2.0678

Max Act: 2.0678. Min Act: -0.0000

Data Index: 479553 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.7923. Min Act: -0.0000

Data Index: 1165428 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.7806. Min Act: -0.0000

Data Index: 780694 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.7318. Min Act: -0.0000

Data Index: 853711 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.6923. Min Act: -0.0000

Data Index: 1478752 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.4967. Min Act: -0.0000

Data Index: 629695 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1372553 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.5649. Min Act: -0.0000

Data Index: 483514 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.6082. Min Act: -0.0000

Data Index: 299857 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.5032. Min Act: -0.0000

Data Index: 823565 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.5091. Min Act: -0.0001

Data Index: 1126045 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.4124. Min Act: -0.0001

Data Index: 398704 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.4978. Min Act: -0.0000

Data Index: 140312 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.5181. Min Act: -0.0000

Data Index: 888685 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.4706. Min Act: -0.0000

Data Index: 876051 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1118386 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.4083. Min Act: -0.0000

Data Index: 311784 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.3874. Min Act: -0.0000

Data Index: 299739 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1375545 (Python Code)

Max Activating Token Index: 623

Text #19

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.3701. Min Act: -0.0000

Data Index: 261440 (C4 (Web Text))

Max Activating Token Index: 112