Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 808 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.5555. Min Act: -0.0001

Data Index: 1332696 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1010546 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.5011. Min Act: -0.0001

Data Index: 640163 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4902. Min Act: -0.0001

Data Index: 190565 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4786. Min Act: -0.0001

Data Index: 1308834 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4992. Min Act: -0.0001

Data Index: 225135 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4667. Min Act: -0.0001

Data Index: 1237602 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4189. Min Act: -0.0001

Data Index: 878861 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4142. Min Act: -0.0001

Data Index: 851369 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4374. Min Act: -0.0001

Data Index: 1324780 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3944. Min Act: -0.0001

Data Index: 809491 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4059. Min Act: -0.0001

Data Index: 371569 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3986. Min Act: -0.0001

Data Index: 96895 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3626. Min Act: -0.0001

Data Index: 351465 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4172. Min Act: -0.0001

Data Index: 1280584 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.4082. Min Act: -0.0001

Data Index: 604 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3707. Min Act: -0.0001

Data Index: 870974 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3492. Min Act: -0.0001

Data Index: 614255 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3643. Min Act: -0.0001

Data Index: 979740 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.5555. Min Range: -0.5555

Max Act: 0.3562. Min Act: -0.0001

Data Index: 153207 (C4 (Web Text))

Max Activating Token Index: 310