Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.5393. Min Act: -0.0001

Data Index: 96626 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3249. Min Act: -0.0001

Data Index: 767713 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1772. Min Act: -0.0001

Data Index: 383858 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1124. Min Act: -0.0001

Data Index: 11946 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1361. Min Act: -0.0001

Data Index: 118119 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.0390. Min Act: -0.0001

Data Index: 525160 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9544. Min Act: -0.0001

Data Index: 968808 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9275. Min Act: -0.0001

Data Index: 1253629 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1302518 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9436. Min Act: -0.0001

Data Index: 1312772 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9142. Min Act: -0.0001

Data Index: 1203447 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9319. Min Act: -0.0001

Data Index: 455584 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9190. Min Act: -0.0001

Data Index: 116442 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.8424. Min Act: -0.0001

Data Index: 70742 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9128. Min Act: -0.0001

Data Index: 98266 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.9299. Min Act: -0.0001

Data Index: 801649 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.8491. Min Act: -0.0001

Data Index: 949581 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.8560. Min Act: -0.0001

Data Index: 673652 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1266434 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.5393. Min Range: -1.5393

Max Act: 0.8351. Min Act: -0.0001

Data Index: 390388 (C4 (Web Text))

Max Activating Token Index: 875