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

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

Neuron 2825 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: 3.9596. Min Range: -3.9596

Max Act: 3.9596. Min Act: -0.0000

Data Index: 1159285 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.4087. Min Act: -0.0000

Data Index: 947635 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.3746. Min Act: -0.0000

Data Index: 818987 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.3794. Min Act: -0.0000

Data Index: 367635 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 3.9596. Min Range: -3.9596

Max Act: 3.0107. Min Act: -0.0000

Data Index: 373682 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.7729. Min Act: -0.0000

Data Index: 725545 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.7358. Min Act: -0.0000

Data Index: 1053112 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.8576. Min Act: -0.0000

Data Index: 994596 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.9596. Min Range: -3.9596

Max Act: 1.9835. Min Act: -0.0000

Data Index: 1275372 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.3695. Min Act: -0.0000

Data Index: 471606 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.7536. Min Act: -0.0000

Data Index: 1341427 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.5350. Min Act: -0.0000

Data Index: 172894 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.5051. Min Act: -0.0000

Data Index: 856104 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.5983. Min Act: -0.0000

Data Index: 211722 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.3316. Min Act: -0.0000

Data Index: 82435 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.3862. Min Act: -0.0000

Data Index: 822219 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1251849 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.4071. Min Act: -0.0000

Data Index: 1056106 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.6435. Min Act: -0.0000

Data Index: 26724 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 3.9596. Min Range: -3.9596

Max Act: 2.4304. Min Act: -0.0000

Data Index: 504416 (C4 (Web Text))

Max Activating Token Index: 695