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

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

Neuron 2978 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: 1.5557. Min Range: -1.5557

Max Act: 1.1913. Min Act: -0.0000

Data Index: 848607 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1387662 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.4607. Min Act: -0.0000

Data Index: 1003737 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1140066 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.2884. Min Act: -0.0000

Data Index: 97810 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.3084. Min Act: -0.0000

Data Index: 246568 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.5557. Min Act: -0.0000

Data Index: 861110 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.2594. Min Act: -0.0000

Data Index: 1354136 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.2633. Min Act: -0.0000

Data Index: 368694 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.2931. Min Act: -0.0000

Data Index: 818339 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.2561. Min Act: -0.0000

Data Index: 217138 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1621010 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1012870 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.1654. Min Act: -0.0000

Data Index: 941217 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1243156 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.1758. Min Act: -0.0000

Data Index: 839607 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.0897. Min Act: -0.0000

Data Index: 966077 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1385823 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.0584. Min Act: -0.0000

Data Index: 160909 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 1.5557. Min Range: -1.5557

Max Act: 1.0479. Min Act: -0.0000

Data Index: 651146 (C4 (Web Text))

Max Activating Token Index: 986