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

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

Neuron 367 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.9518. Min Act: -0.0001

Data Index: 212931 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1301045 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.6287. Min Act: -0.0001

Data Index: 657321 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.6316. Min Act: -0.0001

Data Index: 936419 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5549. Min Act: -0.0001

Data Index: 666439 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.6275. Min Act: -0.0001

Data Index: 941251 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5713. Min Act: -0.0001

Data Index: 310483 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5330. Min Act: -0.0001

Data Index: 190808 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.4946. Min Act: -0.0001

Data Index: 601087 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5761. Min Act: -0.0001

Data Index: 1333789 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.6013. Min Act: -0.0001

Data Index: 1217706 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5525. Min Act: -0.0001

Data Index: 147384 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5895. Min Act: -0.0001

Data Index: 23951 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5607. Min Act: -0.0001

Data Index: 954450 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5340. Min Act: -0.0001

Data Index: 191700 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5579. Min Act: -0.0001

Data Index: 143119 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5299. Min Act: -0.0001

Data Index: 55605 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5143. Min Act: -0.0001

Data Index: 484833 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.5297. Min Act: -0.0001

Data Index: 1273748 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.9518. Min Range: -0.9518

Max Act: 0.4362. Min Act: -0.0001

Data Index: 1238454 (C4 (Web Text))

Max Activating Token Index: 223