Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1781 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.8199. Min Act: -0.0003

Data Index: 271838 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6948. Min Act: -0.0003

Data Index: 246096 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6866. Min Act: -0.0003

Data Index: 975769 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6716. Min Act: -0.0003

Data Index: 1140075 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6264. Min Act: -0.0003

Data Index: 1267901 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.7077. Min Act: -0.0003

Data Index: 185781 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6448. Min Act: -0.0003

Data Index: 1148113 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5938. Min Act: -0.0003

Data Index: 1091932 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6282. Min Act: -0.0003

Data Index: 730039 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6304. Min Act: -0.0003

Data Index: 585509 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6455. Min Act: -0.0003

Data Index: 78448 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5623. Min Act: -0.0003

Data Index: 193337 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6853. Min Act: -0.0003

Data Index: 1337465 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6228. Min Act: -0.0003

Data Index: 814768 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5990. Min Act: -0.0003

Data Index: 495289 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5772. Min Act: -0.0003

Data Index: 739841 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.6068. Min Act: -0.0003

Data Index: 222089 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5556. Min Act: -0.0003

Data Index: 217878 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5913. Min Act: -0.0003

Data Index: 140293 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.8199. Min Range: -0.8199

Max Act: 0.5260. Min Act: -0.0003

Data Index: 661874 (C4 (Web Text))

Max Activating Token Index: 441