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

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

Neuron 1961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2375. Min Act: -0.0001

Data Index: 1347420 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2355. Min Act: -0.0001

Data Index: 472101 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2303. Min Act: -0.0001

Data Index: 1277099 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1112248 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1243663 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1339807 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2037. Min Act: -0.0001

Data Index: 998638 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2082. Min Act: -0.0001

Data Index: 459100 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2080. Min Act: -0.0001

Data Index: 434603 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2119. Min Act: -0.0001

Data Index: 1051972 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1980. Min Act: -0.0001

Data Index: 27313 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2021. Min Act: -0.0001

Data Index: 354077 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2018. Min Act: -0.0001

Data Index: 572364 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1349045 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1111246 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1888. Min Act: -0.0000

Data Index: 335853 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2010. Min Act: -0.0001

Data Index: 623100 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1026368 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1098820 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1778. Min Act: -0.0001

Data Index: 756734 (C4 (Web Text))

Max Activating Token Index: 969