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

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

Neuron 1587 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.2120. Min Act: -0.0001

Data Index: 761314 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.1533. Min Act: -0.0001

Data Index: 1020997 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.1696. Min Act: -0.0001

Data Index: 21451 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.1161. Min Act: -0.0001

Data Index: 244415 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.1032. Min Act: -0.0001

Data Index: 16973 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.1784. Min Act: -0.0001

Data Index: 977947 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.0395. Min Act: -0.0001

Data Index: 1158380 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.9427. Min Act: -0.0001

Data Index: 328280 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.0219. Min Act: -0.0001

Data Index: 772027 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.0812. Min Act: -0.0001

Data Index: 1082317 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.9198. Min Act: -0.0001

Data Index: 1297462 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.2120. Min Range: -1.2120

Max Act: 1.0751. Min Act: -0.0001

Data Index: 1241624 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.9854. Min Act: -0.0001

Data Index: 764567 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.8631. Min Act: -0.0001

Data Index: 103827 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.9776. Min Act: -0.0001

Data Index: 367580 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.8843. Min Act: -0.0001

Data Index: 1259373 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.8211. Min Act: -0.0001

Data Index: 482526 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.7931. Min Act: -0.0001

Data Index: 728643 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.9719. Min Act: -0.0001

Data Index: 1156291 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.2120. Min Range: -1.2120

Max Act: 0.8368. Min Act: -0.0001

Data Index: 1047441 (C4 (Web Text))

Max Activating Token Index: 699