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

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

Neuron 5050 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3105. Min Range: -2.3105

Max Act: 2.3105. Min Act: -0.0000

Data Index: 119777 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 2.3105. Min Range: -2.3105

Max Act: 2.2291. Min Act: -0.0000

Data Index: 887703 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 2.3105. Min Range: -2.3105

Max Act: 2.0385. Min Act: -0.0000

Data Index: 38647 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.8830. Min Act: -0.0000

Data Index: 1215806 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.7497. Min Act: -0.0000

Data Index: 677687 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.9614. Min Act: -0.0000

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.7197. Min Act: -0.0000

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.8086. Min Act: -0.0000

Data Index: 871990 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 2.3105. Min Range: -2.3105

Max Act: 2.0253. Min Act: -0.0000

Data Index: 139762 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.6643. Min Act: -0.0000

Data Index: 129138 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.7734. Min Act: -0.0000

Data Index: 1001153 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.8564. Min Act: -0.0000

Data Index: 1124631 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.5721. Min Act: -0.0000

Data Index: 1014276 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.5619. Min Act: -0.0000

Data Index: 901983 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.6733. Min Act: -0.0000

Data Index: 713460 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.6264. Min Act: -0.0000

Data Index: 1008580 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.7112. Min Act: -0.0000

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.5116. Min Act: -0.0000

Data Index: 528332 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.5973. Min Act: -0.0000

Data Index: 195376 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 2.3105. Min Range: -2.3105

Max Act: 1.6343. Min Act: -0.0000

Data Index: 55339 (C4 (Web Text))

Max Activating Token Index: 915