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

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

Neuron 333 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: 0.2504. Min Range: -0.2504

Max Act: 0.2504. Min Act: -0.0001

Data Index: 561784 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2401. Min Act: -0.0001

Data Index: 831923 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1314842 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2473. Min Act: -0.0001

Data Index: 617920 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2363. Min Act: -0.0001

Data Index: 450099 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2311. Min Act: -0.0001

Data Index: 840304 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2312. Min Act: -0.0001

Data Index: 819708 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2312. Min Act: -0.0001

Data Index: 964948 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2251. Min Act: -0.0001

Data Index: 1167119 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2318. Min Act: -0.0001

Data Index: 648532 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2233. Min Act: -0.0001

Data Index: 761085 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2135. Min Act: -0.0001

Data Index: 342017 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2219. Min Act: -0.0001

Data Index: 433407 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2047. Min Act: -0.0001

Data Index: 866096 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2188. Min Act: -0.0001

Data Index: 425928 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1180121 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2176. Min Act: -0.0001

Data Index: 920487 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2003. Min Act: -0.0001

Data Index: 992017 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.1992. Min Act: -0.0001

Data Index: 901974 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.2504. Min Range: -0.2504

Max Act: 0.2037. Min Act: -0.0001

Data Index: 96580 (C4 (Web Text))

Max Activating Token Index: 957