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

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

Neuron 876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6865. Min Act: -0.0000

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.8354. Min Act: -0.0001

Data Index: 496855 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.7453. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.7500. Min Act: -0.0001

Data Index: 1545418 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.7518. Min Act: -0.0001

Data Index: 1654625 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6562. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5004. Min Act: -0.0001

Data Index: 477621 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5105. Min Act: -0.0001

Data Index: 988105 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5083. Min Act: -0.0001

Data Index: 629253 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4052. Min Act: -0.0001

Data Index: 1129384 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5754. Min Act: -0.0000

Data Index: 978039 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4543. Min Act: -0.0001

Data Index: 888573 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4187. Min Act: -0.0000

Data Index: 716624 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4651. Min Act: -0.0000

Data Index: 1503641 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4528. Min Act: -0.0001

Data Index: 223583 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.3889. Min Act: -0.0000

Data Index: 1132398 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.3353. Min Act: -0.0000

Data Index: 55474 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4385. Min Act: -0.0001

Data Index: 687529 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4035. Min Act: -0.0001

Data Index: 1419769 (Python Code)

Max Activating Token Index: 423

Text #19

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1026843 (C4 (Web Text))

Max Activating Token Index: 1010