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

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

Neuron 3749 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: 3.1084. Min Range: -3.1084

Max Act: 2.9890. Min Act: -0.0000

Data Index: 610783 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 3.1084. Min Range: -3.1084

Max Act: 3.1084. Min Act: -0.0000

Data Index: 168277 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.8065. Min Act: -0.0000

Data Index: 875583 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.5868. Min Act: -0.0000

Data Index: 1330637 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.4242. Min Act: -0.0000

Data Index: 1344436 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.4077. Min Act: -0.0000

Data Index: 141806 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.2860. Min Act: -0.0000

Data Index: 562785 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.3828. Min Act: -0.0000

Data Index: 1094005 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.3748. Min Act: -0.0000

Data Index: 1232709 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.3717. Min Act: -0.0000

Data Index: 481759 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.3105. Min Act: -0.0000

Data Index: 1040881 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.3028. Min Act: -0.0000

Data Index: 756305 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.1833. Min Act: -0.0000

Data Index: 737906 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.2913. Min Act: -0.0000

Data Index: 984674 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.2828. Min Act: -0.0000

Data Index: 563572 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.2860. Min Act: -0.0000

Data Index: 539121 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.1682. Min Act: -0.0000

Data Index: 558678 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.2824. Min Act: -0.0000

Data Index: 22397 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.2855. Min Act: -0.0000

Data Index: 274830 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 3.1084. Min Range: -3.1084

Max Act: 2.2762. Min Act: -0.0000

Data Index: 697591 (C4 (Web Text))

Max Activating Token Index: 38