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

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

Neuron 2773 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0716. Min Range: -1.0716

Max Act: 1.0716. Min Act: -0.0000

Data Index: 577260 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.9673. Min Act: -0.0000

Data Index: 303196 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8908. Min Act: -0.0000

Data Index: 672734 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1094385 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8673. Min Act: -0.0000

Data Index: 679663 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8807. Min Act: -0.0000

Data Index: 455253 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1150595 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8511. Min Act: -0.0000

Data Index: 230309 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1301899 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8368. Min Act: -0.0000

Data Index: 528589 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8284. Min Act: -0.0000

Data Index: 920290 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8517. Min Act: -0.0000

Data Index: 485031 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8414. Min Act: -0.0000

Data Index: 325612 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8138. Min Act: -0.0000

Data Index: 104596 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8113. Min Act: -0.0000

Data Index: 394190 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8097. Min Act: -0.0000

Data Index: 766357 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1216492 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.8153. Min Act: -0.0000

Data Index: 401067 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.7840. Min Act: -0.0000

Data Index: 897643 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.0716. Min Range: -1.0716

Max Act: 0.7529. Min Act: -0.0000

Data Index: 607903 (C4 (Web Text))

Max Activating Token Index: 993