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

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

Neuron 3803 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.8682. Min Act: -0.0000

Data Index: 407472 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.4620. Min Act: -0.0000

Data Index: 516432 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.3209. Min Act: -0.0000

Data Index: 980796 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.2716. Min Act: -0.0000

Data Index: 384087 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.0903. Min Act: -0.0000

Data Index: 437750 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.0892. Min Act: -0.0000

Data Index: 551137 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.1218. Min Act: -0.0000

Data Index: 61815 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 2.8682. Min Range: -2.8682

Max Act: 2.0621. Min Act: -0.0000

Data Index: 1021080 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.9656. Min Act: -0.0000

Data Index: 434145 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.9464. Min Act: -0.0000

Data Index: 786895 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.9966. Min Act: -0.0000

Data Index: 556495 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.9383. Min Act: -0.0000

Data Index: 783324 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.8755. Min Act: -0.0000

Data Index: 653041 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.9018. Min Act: -0.0000

Data Index: 91303 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1085369 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.8736. Min Act: -0.0000

Data Index: 328882 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.7515. Min Act: -0.0000

Data Index: 133190 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.7742. Min Act: -0.0000

Data Index: 218915 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.9197. Min Act: -0.0000

Data Index: 87818 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 2.8682. Min Range: -2.8682

Max Act: 1.7695. Min Act: -0.0000

Data Index: 1247402 (C4 (Web Text))

Max Activating Token Index: 42