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

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

Neuron 3702 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0037. Min Act: -0.0003

Data Index: 654237 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1171983 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 264213 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 416623 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0003

Data Index: 861766 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0003

Data Index: 588820 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0003

Data Index: 335256 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0003

Data Index: 16428 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 175476 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 883168 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0003

Data Index: 624012 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 94413 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 1353277 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0003

Data Index: 1223138 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 892749 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0003

Data Index: 371982 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 94159 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 784056 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0003

Data Index: 389653 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0003

Data Index: 685960 (C4 (Web Text))

Max Activating Token Index: 762