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

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

Neuron 5004 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1127. Min Range: -1.1127

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1614952 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1192697 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8950. Min Act: -0.0000

Data Index: 35089 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.8312. Min Act: -0.0000

Data Index: 869234 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7823. Min Act: -0.0000

Data Index: 136041 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1475854 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1392324 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7247. Min Act: -0.0000

Data Index: 402181 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6751. Min Act: -0.0000

Data Index: 427921 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.7203. Min Act: -0.0000

Data Index: 742837 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1564619 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1619429 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6758. Min Act: -0.0000

Data Index: 420871 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.5832. Min Act: -0.0000

Data Index: 398839 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1656401 (Python Code)

Max Activating Token Index: 968

Text #15

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1463064 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6278. Min Act: -0.0000

Data Index: 255541 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6187. Min Act: -0.0000

Data Index: 205948 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.6478. Min Act: -0.0000

Data Index: 614567 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.1127. Min Range: -1.1127

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1575550 (Python Code)

Max Activating Token Index: 104