Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4377 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1014703 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1921. Min Act: -0.0000

Data Index: 464820 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.2007. Min Act: -0.0000

Data Index: 931826 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.2126. Min Act: -0.0000

Data Index: 720070 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1249. Min Act: -0.0000

Data Index: 87916 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1253. Min Act: -0.0000

Data Index: 469814 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1158. Min Act: -0.0000

Data Index: 128284 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1134262 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1358991 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1099. Min Act: -0.0000

Data Index: 143282 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1135. Min Act: -0.0000

Data Index: 714058 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1134. Min Act: -0.0000

Data Index: 366904 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1108. Min Act: -0.0000

Data Index: 591462 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1107. Min Act: -0.0000

Data Index: 939044 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1125611 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.0979. Min Act: -0.0000

Data Index: 229569 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.0962. Min Act: -0.0000

Data Index: 419685 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1642828 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.0991. Min Act: -0.0000

Data Index: 457177 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.2126. Min Range: -0.2126

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1065465 (C4 (Web Text))

Max Activating Token Index: 371