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

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

Neuron 2093 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.9937. Min Act: -0.0001

Data Index: 1247599 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.8860. Min Act: -0.0001

Data Index: 1090084 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.8075. Min Act: -0.0001

Data Index: 437559 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7896. Min Act: -0.0001

Data Index: 1067325 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7984. Min Act: -0.0001

Data Index: 1199953 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7643. Min Act: -0.0001

Data Index: 311269 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7604. Min Act: -0.0001

Data Index: 1282522 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.6876. Min Act: -0.0001

Data Index: 142889 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7501. Min Act: -0.0001

Data Index: 208409 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7241. Min Act: -0.0001

Data Index: 830924 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.6959. Min Act: -0.0001

Data Index: 114872 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7118. Min Act: -0.0001

Data Index: 973415 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7301. Min Act: -0.0001

Data Index: 860422 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7089. Min Act: -0.0001

Data Index: 157298 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7248. Min Act: -0.0001

Data Index: 327738 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.7042. Min Act: -0.0001

Data Index: 757671 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.6599. Min Act: -0.0001

Data Index: 266276 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.6737. Min Act: -0.0001

Data Index: 198921 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.6899. Min Act: -0.0001

Data Index: 1134888 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.9937. Min Range: -0.9937

Max Act: 0.6207. Min Act: -0.0001

Data Index: 397442 (C4 (Web Text))

Max Activating Token Index: 149