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

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

Neuron 2397 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: 3.1305. Min Range: -3.1305

Max Act: 3.1305. Min Act: -0.0000

Data Index: 225884 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.8950. Min Act: -0.0000

Data Index: 1226755 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 3.1305. Min Range: -3.1305

Max Act: 3.0332. Min Act: -0.0000

Data Index: 664966 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.4096. Min Act: -0.0000

Data Index: 573558 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.4936. Min Act: -0.0000

Data Index: 1342771 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.4605. Min Act: -0.0000

Data Index: 1027835 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1182219 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.3005. Min Act: -0.0000

Data Index: 694642 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.3263. Min Act: -0.0000

Data Index: 970686 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.5575. Min Act: -0.0000

Data Index: 1350824 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.2407. Min Act: -0.0000

Data Index: 902698 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.2378. Min Act: -0.0000

Data Index: 1218290 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 3.1305. Min Range: -3.1305

Max Act: 1.9815. Min Act: -0.0000

Data Index: 1059796 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.2112. Min Act: -0.0000

Data Index: 297337 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.0945. Min Act: -0.0000

Data Index: 155445 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.3146. Min Act: -0.0000

Data Index: 409062 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.4074. Min Act: -0.0000

Data Index: 747621 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.0731. Min Act: -0.0000

Data Index: 859415 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.1853. Min Act: -0.0000

Data Index: 202636 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 3.1305. Min Range: -3.1305

Max Act: 2.0624. Min Act: -0.0000

Data Index: 634029 (C4 (Web Text))

Max Activating Token Index: 639