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

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

Neuron 3178 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: 2.1446. Min Range: -2.1446

Max Act: 2.1446. Min Act: -0.0000

Data Index: 1146297 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.8935. Min Act: -0.0000

Data Index: 1307965 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.5914. Min Act: -0.0000

Data Index: 1305708 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.9007. Min Act: -0.0001

Data Index: 327421 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.6624. Min Act: -0.0000

Data Index: 243086 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.5213. Min Act: -0.0000

Data Index: 215814 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1019030 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.4683. Min Act: -0.0000

Data Index: 452307 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.5132. Min Act: -0.0001

Data Index: 927752 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.5009. Min Act: -0.0000

Data Index: 562386 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.3454. Min Act: -0.0001

Data Index: 1271804 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.3872. Min Act: -0.0000

Data Index: 428231 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.3202. Min Act: -0.0000

Data Index: 618327 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.3580. Min Act: -0.0001

Data Index: 633935 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.3451. Min Act: -0.0001

Data Index: 1077403 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1058989 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.3804. Min Act: -0.0001

Data Index: 882125 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1042116 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.2430. Min Act: -0.0000

Data Index: 432133 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 2.1446. Min Range: -2.1446

Max Act: 1.3961. Min Act: -0.0001

Data Index: 1073797 (C4 (Web Text))

Max Activating Token Index: 80