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

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

Neuron 3779 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: 0.5996. Min Range: -0.5996

Max Act: 0.5972. Min Act: -0.0001

Data Index: 1262593 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5996. Min Act: -0.0002

Data Index: 328351 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5593. Min Act: -0.0002

Data Index: 1234265 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5295. Min Act: -0.0001

Data Index: 929845 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4500. Min Act: -0.0001

Data Index: 634433 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5770. Min Act: -0.0002

Data Index: 372537 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5387. Min Act: -0.0002

Data Index: 416575 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5196. Min Act: -0.0002

Data Index: 106795 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5980. Min Act: -0.0002

Data Index: 581585 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5301. Min Act: -0.0002

Data Index: 1097273 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5650. Min Act: -0.0001

Data Index: 744167 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5073. Min Act: -0.0001

Data Index: 1047077 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5277. Min Act: -0.0002

Data Index: 233460 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5254. Min Act: -0.0002

Data Index: 890790 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5356. Min Act: -0.0002

Data Index: 883129 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5157. Min Act: -0.0002

Data Index: 1265979 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5147. Min Act: -0.0002

Data Index: 611097 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5114. Min Act: -0.0001

Data Index: 441886 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4922. Min Act: -0.0002

Data Index: 1009239 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5327. Min Act: -0.0001

Data Index: 205819 (C4 (Web Text))

Max Activating Token Index: 237