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

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

Neuron 5193 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.6857. Min Act: -0.0000

Data Index: 519124 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.5161. Min Act: -0.0000

Data Index: 513029 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.0601. Min Act: -0.0000

Data Index: 229015 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.0558. Min Act: -0.0000

Data Index: 882010 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 3.6857. Min Range: -3.6857

Max Act: 3.0463. Min Act: -0.0000

Data Index: 270815 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.8632. Min Act: -0.0000

Data Index: 547983 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7205. Min Act: 0.0000

Data Index: 166213 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.8695. Min Act: -0.0000

Data Index: 201953 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7374. Min Act: -0.0000

Data Index: 161581 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7081. Min Act: -0.0000

Data Index: 65358 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7959. Min Act: -0.0000

Data Index: 1290920 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7888. Min Act: -0.0000

Data Index: 1057066 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7560. Min Act: -0.0000

Data Index: 932535 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.5952. Min Act: -0.0000

Data Index: 753808 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.5981. Min Act: -0.0000

Data Index: 332566 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7081. Min Act: -0.0000

Data Index: 200450 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.7020. Min Act: -0.0000

Data Index: 876296 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.5380. Min Act: -0.0000

Data Index: 193764 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.5060. Min Act: 0.0000

Data Index: 1008673 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 3.6857. Min Range: -3.6857

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1276085 (C4 (Web Text))

Max Activating Token Index: 866