Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1001923 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2847. Min Act: -0.0001

Data Index: 837718 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2784. Min Act: -0.0000

Data Index: 272283 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1179119 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2475. Min Act: -0.0001

Data Index: 140023 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2549. Min Act: -0.0001

Data Index: 699047 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1342141 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1832. Min Act: -0.0000

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1737. Min Act: -0.0001

Data Index: 828644 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1859. Min Act: -0.0000

Data Index: 567166 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1650762 (Python Code)

Max Activating Token Index: 949

Text #11

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1787. Min Act: -0.0001

Data Index: 511336 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1741. Min Act: -0.0000

Data Index: 388392 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1620284 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1550011 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1494346 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1760. Min Act: -0.0001

Data Index: 1401557 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1462750 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1213459 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1468316 (Python Code)

Max Activating Token Index: 953