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

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

Neuron 85 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: 0.7796. Min Range: -0.7796

Max Act: 0.7796. Min Act: -0.0001

Data Index: 922773 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.6126. Min Act: -0.0001

Data Index: 1507794 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.6370. Min Act: -0.0001

Data Index: 533865 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1565967 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1402133 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1523901 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5739. Min Act: -0.0001

Data Index: 785317 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.4584. Min Act: -0.0001

Data Index: 1627765 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5080. Min Act: -0.0001

Data Index: 1604054 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5690. Min Act: -0.0001

Data Index: 1526434 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5390. Min Act: -0.0001

Data Index: 1598183 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5298. Min Act: -0.0001

Data Index: 268018 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5220. Min Act: -0.0001

Data Index: 432557 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5251. Min Act: -0.0001

Data Index: 1607343 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5041. Min Act: -0.0002

Data Index: 1167791 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5273. Min Act: -0.0002

Data Index: 156651 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5260. Min Act: -0.0001

Data Index: 226783 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5067. Min Act: -0.0002

Data Index: 1422187 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.4958. Min Act: -0.0002

Data Index: 1608148 (Python Code)

Max Activating Token Index: 623

Text #19

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1619258 (Python Code)

Max Activating Token Index: 984