Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 657 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1090916 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0287. Min Act: -0.0005

Data Index: 1037268 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0299. Min Act: -0.0005

Data Index: 813651 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0295. Min Act: -0.0005

Data Index: 815458 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0005

Data Index: 6883 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0298. Min Act: -0.0005

Data Index: 828913 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0281. Min Act: -0.0005

Data Index: 805356 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0269. Min Act: -0.0005

Data Index: 284188 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0281. Min Act: -0.0005

Data Index: 965692 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0280. Min Act: -0.0005

Data Index: 554701 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0289. Min Act: -0.0005

Data Index: 169555 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0300. Min Act: -0.0005

Data Index: 105096 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0288. Min Act: -0.0005

Data Index: 740104 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0272. Min Act: -0.0005

Data Index: 619032 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0271. Min Act: -0.0005

Data Index: 996114 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0287. Min Act: -0.0005

Data Index: 19066 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0285. Min Act: -0.0005

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0263. Min Act: -0.0005

Data Index: 1004948 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0278. Min Act: -0.0005

Data Index: 833085 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0276. Min Act: -0.0005

Data Index: 961176 (C4 (Web Text))

Max Activating Token Index: 178