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

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

Neuron 3682 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.3698. Min Act: -0.0000

Data Index: 604690 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.3288. Min Act: -0.0001

Data Index: 613857 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.3173. Min Act: -0.0000

Data Index: 754414 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.3143. Min Act: -0.0001

Data Index: 58305 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1292644 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2852. Min Act: -0.0000

Data Index: 423011 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2503. Min Act: -0.0000

Data Index: 672278 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1324368 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2184. Min Act: -0.0001

Data Index: 594867 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1226836 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1579710 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2129. Min Act: -0.0001

Data Index: 697106 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1285808 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2214. Min Act: -0.0001

Data Index: 387757 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2118. Min Act: -0.0001

Data Index: 971575 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2289. Min Act: -0.0000

Data Index: 12392 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.1719. Min Act: -0.0000

Data Index: 821665 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.2066. Min Act: -0.0001

Data Index: 143113 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1145532 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.3698. Min Range: -0.3698

Max Act: 0.1894. Min Act: -0.0001

Data Index: 462690 (C4 (Web Text))

Max Activating Token Index: 558