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

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

Neuron 3376 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.6945. Min Act: -0.0000

Data Index: 1509473 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.4001. Min Act: -0.0000

Data Index: 1215358 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.0964. Min Act: -0.0000

Data Index: 519508 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.1708. Min Act: -0.0000

Data Index: 1234037 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.0019. Min Act: -0.0000

Data Index: 443070 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.1152. Min Act: -0.0000

Data Index: 747460 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.0826. Min Act: -0.0000

Data Index: 1114907 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.8326. Min Act: -0.0000

Data Index: 150308 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.0300. Min Act: -0.0000

Data Index: 806778 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 2.6945. Min Range: -2.6945

Max Act: 2.0369. Min Act: -0.0000

Data Index: 1221522 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.9934. Min Act: -0.0000

Data Index: 450763 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1146117 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.8394. Min Act: -0.0000

Data Index: 10340 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.9025. Min Act: -0.0000

Data Index: 1088941 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.8167. Min Act: -0.0000

Data Index: 390533 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.7771. Min Act: -0.0000

Data Index: 1104834 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.6468. Min Act: -0.0000

Data Index: 33411 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.6290. Min Act: -0.0000

Data Index: 771983 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.7395. Min Act: -0.0000

Data Index: 521463 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 2.6945. Min Range: -2.6945

Max Act: 1.7231. Min Act: -0.0000

Data Index: 640117 (C4 (Web Text))

Max Activating Token Index: 849