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

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

Neuron 5173 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2388. Min Range: -3.2388

Max Act: 3.2388. Min Act: -0.0000

Data Index: 967764 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.8103. Min Act: -0.0000

Data Index: 1315536 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.4273. Min Act: -0.0000

Data Index: 1119260 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.2189. Min Act: -0.0000

Data Index: 317684 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.3085. Min Act: -0.0000

Data Index: 1118366 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.2693. Min Act: -0.0000

Data Index: 991261 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1052. Min Act: -0.0000

Data Index: 244529 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1775. Min Act: -0.0000

Data Index: 4304 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1692. Min Act: -0.0000

Data Index: 1337693 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1717. Min Act: -0.0000

Data Index: 1019968 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.2669. Min Act: -0.0000

Data Index: 712668 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.2527. Min Act: -0.0000

Data Index: 31571 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1375. Min Act: -0.0000

Data Index: 666452 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1286. Min Act: -0.0000

Data Index: 614654 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1217. Min Act: -0.0000

Data Index: 1224811 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.0280. Min Act: -0.0000

Data Index: 896433 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.1019. Min Act: -0.0000

Data Index: 696203 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 3.2388. Min Range: -3.2388

Max Act: 1.9593. Min Act: -0.0000

Data Index: 80347 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 3.2388. Min Range: -3.2388

Max Act: 2.0453. Min Act: -0.0000

Data Index: 831700 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 3.2388. Min Range: -3.2388

Max Act: 1.9309. Min Act: -0.0000

Data Index: 1348738 (C4 (Web Text))

Max Activating Token Index: 163