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

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

Neuron 4364 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: 1.1741. Min Range: -1.1741

Max Act: 1.1741. Min Act: -0.0000

Data Index: 796742 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1275123 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.1139. Min Act: -0.0000

Data Index: 109408 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.0496. Min Act: -0.0000

Data Index: 610087 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.1127. Min Act: -0.0000

Data Index: 390806 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.0942. Min Act: -0.0000

Data Index: 952557 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1302952 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.1210. Min Act: -0.0001

Data Index: 795210 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9719. Min Act: -0.0000

Data Index: 951170 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9671. Min Act: -0.0001

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9612. Min Act: -0.0000

Data Index: 145738 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1027713 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.0062. Min Act: -0.0000

Data Index: 516895 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.1741. Min Range: -1.1741

Max Act: 1.0312. Min Act: -0.0000

Data Index: 611221 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1308167 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9845. Min Act: -0.0000

Data Index: 644292 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9215. Min Act: -0.0000

Data Index: 161019 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1555490 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9470. Min Act: -0.0000

Data Index: 607785 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.1741. Min Range: -1.1741

Max Act: 0.9328. Min Act: -0.0000

Data Index: 967308 (C4 (Web Text))

Max Activating Token Index: 881