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

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

Neuron 5831 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.3570. Min Act: -0.0000

Data Index: 895089 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1547029 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1084909 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2387. Min Act: -0.0000

Data Index: 23315 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2751. Min Act: -0.0000

Data Index: 979533 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1612. Min Act: -0.0000

Data Index: 612855 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1057684 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1115071 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1043. Min Act: -0.0000

Data Index: 789443 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1149. Min Act: -0.0000

Data Index: 251449 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1184895 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1203905 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0077. Min Act: -0.0000

Data Index: 809030 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1221332 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1242374 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0666. Min Act: -0.0000

Data Index: 183356 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1572895 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0886. Min Act: -0.0000

Data Index: 1333210 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9606. Min Act: -0.0000

Data Index: 148523 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1066295 (C4 (Web Text))

Max Activating Token Index: 308