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

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

Neuron 3621 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6495. Min Act: -0.0000

Data Index: 757055 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.7398. Min Act: -0.0000

Data Index: 70355 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6918. Min Act: -0.0000

Data Index: 731320 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6673. Min Act: -0.0000

Data Index: 907190 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6185. Min Act: -0.0000

Data Index: 1322224 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6866. Min Act: -0.0001

Data Index: 560279 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6763. Min Act: -0.0000

Data Index: 737037 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1242500 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6031. Min Act: -0.0000

Data Index: 1299239 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1041925 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.4903. Min Act: -0.0000

Data Index: 649782 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.5550. Min Act: -0.0000

Data Index: 507105 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.6556. Min Act: -0.0000

Data Index: 1357336 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.5365. Min Act: -0.0000

Data Index: 876580 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.4935. Min Act: -0.0000

Data Index: 565984 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.5249. Min Act: -0.0000

Data Index: 958728 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.4435. Min Act: -0.0000

Data Index: 28918 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.3386. Min Act: -0.0000

Data Index: 261248 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.3982. Min Act: -0.0000

Data Index: 1267765 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.7398. Min Range: -1.7398

Max Act: 1.4720. Min Act: -0.0000

Data Index: 764789 (C4 (Web Text))

Max Activating Token Index: 673