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

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

Neuron 3019 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0066. Min Range: -5.0066

Max Act: 5.0066. Min Act: -0.0001

Data Index: 1099718 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.7684. Min Act: -0.0001

Data Index: 823237 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.7164. Min Act: -0.0001

Data Index: 631983 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.4325. Min Act: -0.0001

Data Index: 830641 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.4993. Min Act: -0.0002

Data Index: 1080111 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.2722. Min Act: -0.0002

Data Index: 424606 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.4403. Min Act: -0.0002

Data Index: 574160 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.3602. Min Act: -0.0001

Data Index: 840454 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.1771. Min Act: -0.0001

Data Index: 219789 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.3247. Min Act: -0.0002

Data Index: 475879 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 5.0066. Min Range: -5.0066

Max Act: 3.9524. Min Act: -0.0001

Data Index: 647450 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 5.0066. Min Range: -5.0066

Max Act: 3.9333. Min Act: -0.0001

Data Index: 105454 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.3965. Min Act: -0.0001

Data Index: 1227557 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.1135. Min Act: -0.0001

Data Index: 706930 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 5.0066. Min Range: -5.0066

Max Act: 3.8621. Min Act: -0.0001

Data Index: 414894 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.0442. Min Act: -0.0001

Data Index: 699719 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.1434. Min Act: -0.0002

Data Index: 98132 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 5.0066. Min Range: -5.0066

Max Act: 4.0205. Min Act: -0.0001

Data Index: 327631 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 5.0066. Min Range: -5.0066

Max Act: 3.7808. Min Act: -0.0001

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 5.0066. Min Range: -5.0066

Max Act: 3.9333. Min Act: -0.0002

Data Index: 604743 (C4 (Web Text))

Max Activating Token Index: 434