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

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

Neuron 3925 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: 0.8149. Min Range: -0.8149

Max Act: 0.8149. Min Act: -0.0000

Data Index: 496502 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7728. Min Act: -0.0000

Data Index: 537914 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7791. Min Act: -0.0000

Data Index: 109655 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7213. Min Act: -0.0000

Data Index: 845262 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7455. Min Act: -0.0000

Data Index: 114972 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7036. Min Act: -0.0000

Data Index: 811173 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7726. Min Act: -0.0000

Data Index: 717166 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1185469 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1045411 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1047985 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6712. Min Act: -0.0000

Data Index: 120075 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1044236 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6755. Min Act: -0.0000

Data Index: 56240 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6404. Min Act: -0.0000

Data Index: 874504 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6225. Min Act: -0.0000

Data Index: 3064 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1282605 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1356684 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1181098 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1118001 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6057. Min Act: -0.0000

Data Index: 219784 (C4 (Web Text))

Max Activating Token Index: 910