Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 538 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1384737 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1601598 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1380713 (Python Code)

Max Activating Token Index: 121

Text #3

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1382205 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1286895 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.2697. Min Range: -1.2697

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1625587 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1513850 (Python Code)

Max Activating Token Index: 506

Text #7

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1610544 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1532732 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1545410 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1543581 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1504577 (Python Code)

Max Activating Token Index: 153

Text #12

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1624539 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1538580 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1491091 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1159258 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1401345 (Python Code)

Max Activating Token Index: 681

Text #17

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1474426 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1430933 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 1.2697. Min Range: -1.2697

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1653387 (Python Code)

Max Activating Token Index: 6