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

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

Neuron 1712 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.9670. Min Act: -0.0000

Data Index: 730508 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.9376. Min Act: -0.0000

Data Index: 23162 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1426569 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1486747 (Python Code)

Max Activating Token Index: 318

Text #4

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7508. Min Act: -0.0000

Data Index: 101357 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1258666 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6441. Min Act: -0.0000

Data Index: 476386 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1364386 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1462862 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1427491 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1273538 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5939. Min Act: -0.0000

Data Index: 178739 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6251. Min Act: -0.0000

Data Index: 359524 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5749. Min Act: -0.0000

Data Index: 5210 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1119734 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1439620 (Python Code)

Max Activating Token Index: 963

Text #17

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1364485 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1626103 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5693. Min Act: -0.0000

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 783