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

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

Neuron 5706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.1427. Min Range: -9.1427

Max Act: 9.1427. Min Act: -0.0000

Data Index: 1072817 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.7881. Min Act: -0.0000

Data Index: 498097 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 9.1427. Min Range: -9.1427

Max Act: 8.2806. Min Act: -0.0000

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.9357. Min Act: -0.0000

Data Index: 1040272 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 9.1427. Min Range: -9.1427

Max Act: 8.0510. Min Act: -0.0000

Data Index: 292081 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.9967. Min Act: -0.0000

Data Index: 411290 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 9.1427. Min Range: -9.1427

Max Act: 8.0981. Min Act: -0.0000

Data Index: 658621 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.7310. Min Act: -0.0000

Data Index: 1314882 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.5558. Min Act: -0.0000

Data Index: 1315579 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.7150. Min Act: -0.0000

Data Index: 1300914 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.6218. Min Act: -0.0000

Data Index: 875076 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.5474. Min Act: -0.0000

Data Index: 700295 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.9244. Min Act: -0.0000

Data Index: 142178 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.6584. Min Act: -0.0000

Data Index: 828151 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.5864. Min Act: -0.0000

Data Index: 573235 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.1875. Min Act: -0.0000

Data Index: 1283479 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.3018. Min Act: -0.0000

Data Index: 1294615 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.6039. Min Act: -0.0000

Data Index: 266478 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 9.1427. Min Range: -9.1427

Max Act: 7.4130. Min Act: -0.0000

Data Index: 221611 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 9.1427. Min Range: -9.1427

Max Act: 6.9776. Min Act: -0.0000

Data Index: 897704 (C4 (Web Text))

Max Activating Token Index: 852