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

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

Neuron 4548 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: 1.4165. Min Range: -1.4165

Max Act: 1.2631. Min Act: -0.0000

Data Index: 395106 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.4165. Min Act: -0.0000

Data Index: 640671 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.1548. Min Act: -0.0000

Data Index: 1009292 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1064655 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1193230 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.1787. Min Act: -0.0000

Data Index: 844604 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.2015. Min Act: -0.0000

Data Index: 427350 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.1093. Min Act: -0.0000

Data Index: 577587 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0414. Min Act: -0.0000

Data Index: 480807 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1011474 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9396. Min Act: -0.0000

Data Index: 422636 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0265. Min Act: -0.0000

Data Index: 610312 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9882. Min Act: -0.0000

Data Index: 965914 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1300848 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0633. Min Act: -0.0000

Data Index: 185782 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9742. Min Act: -0.0000

Data Index: 856325 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9992. Min Act: -0.0000

Data Index: 540544 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0016. Min Act: -0.0000

Data Index: 316005 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.4165. Min Range: -1.4165

Max Act: 1.0319. Min Act: -0.0000

Data Index: 366590 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.4165. Min Range: -1.4165

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1161925 (C4 (Web Text))

Max Activating Token Index: 632