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

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

Neuron 991 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5571. Min Act: -0.0000

Data Index: 436878 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1138244 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5954. Min Act: -0.0000

Data Index: 808554 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5237. Min Act: -0.0000

Data Index: 996363 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5278. Min Act: -0.0000

Data Index: 449214 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5114. Min Act: -0.0000

Data Index: 96665 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5746. Min Act: -0.0000

Data Index: 542279 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1350397 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1269389 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5056. Min Act: -0.0000

Data Index: 608027 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1309836 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5079. Min Act: -0.0000

Data Index: 725707 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1209222 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4801. Min Act: -0.0000

Data Index: 266175 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1301012 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4624. Min Act: -0.0000

Data Index: 767290 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1029459 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4737. Min Act: -0.0000

Data Index: 468118 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4499. Min Act: -0.0000

Data Index: 407002 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5155. Min Act: -0.0000

Data Index: 13133 (C4 (Web Text))

Max Activating Token Index: 149