Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1088751 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1901. Min Act: -0.0001

Data Index: 283403 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1741. Min Act: -0.0000

Data Index: 393857 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1708. Min Act: -0.0000

Data Index: 177411 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1662. Min Act: -0.0001

Data Index: 274000 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1280972 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1510. Min Act: -0.0000

Data Index: 941836 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1262821 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1571. Min Act: -0.0000

Data Index: 239644 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1430. Min Act: -0.0000

Data Index: 218406 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1135310 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1368. Min Act: -0.0000

Data Index: 688933 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1194. Min Act: -0.0001

Data Index: 771692 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1236. Min Act: -0.0000

Data Index: 724379 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1186. Min Act: -0.0000

Data Index: 448664 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1102. Min Act: -0.0001

Data Index: 339942 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1120595 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1198. Min Act: -0.0000

Data Index: 332407 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1268723 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1060766 (C4 (Web Text))

Max Activating Token Index: 386