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

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

Neuron 452 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9668. Min Act: -0.0001

Data Index: 77853 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1247023 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9213. Min Act: -0.0001

Data Index: 1015386 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8888. Min Act: -0.0001

Data Index: 1280432 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7682. Min Act: -0.0001

Data Index: 221813 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7959. Min Act: -0.0001

Data Index: 133371 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.0287. Min Range: -1.0287

Max Act: 1.0287. Min Act: -0.0001

Data Index: 734893 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8870. Min Act: -0.0001

Data Index: 837067 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8389. Min Act: -0.0001

Data Index: 602531 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8818. Min Act: -0.0001

Data Index: 274409 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8553. Min Act: -0.0001

Data Index: 996182 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8230. Min Act: -0.0001

Data Index: 469253 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7725. Min Act: -0.0001

Data Index: 239037 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8383. Min Act: -0.0001

Data Index: 243577 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1149132 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7646. Min Act: -0.0001

Data Index: 555998 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8534. Min Act: -0.0001

Data Index: 716474 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8521. Min Act: -0.0001

Data Index: 630927 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8762. Min Act: -0.0001

Data Index: 167741 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8001. Min Act: -0.0001

Data Index: 976690 (C4 (Web Text))

Max Activating Token Index: 114