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

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

Neuron 3691 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7892. Min Act: -0.0001

Data Index: 659382 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7687. Min Act: -0.0001

Data Index: 1043107 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.9047. Min Act: -0.0001

Data Index: 965169 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.8852. Min Act: -0.0001

Data Index: 94211 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7528. Min Act: -0.0002

Data Index: 26569 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.8113. Min Act: -0.0002

Data Index: 1322426 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7534. Min Act: -0.0002

Data Index: 1288629 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.8424. Min Act: -0.0002

Data Index: 1301518 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7601. Min Act: -0.0001

Data Index: 1301253 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7027. Min Act: -0.0001

Data Index: 725599 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5977. Min Act: -0.0002

Data Index: 855577 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6916. Min Act: -0.0001

Data Index: 344931 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.7155. Min Act: -0.0001

Data Index: 871070 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6931. Min Act: -0.0001

Data Index: 667605 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6088. Min Act: -0.0001

Data Index: 209064 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6310. Min Act: -0.0001

Data Index: 920353 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6483. Min Act: -0.0001

Data Index: 1346050 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.6176. Min Act: -0.0002

Data Index: 445041 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5341. Min Act: -0.0002

Data Index: 509689 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5293. Min Act: -0.0001

Data Index: 921894 (C4 (Web Text))

Max Activating Token Index: 672