Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1065774 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5609. Min Act: -0.0000

Data Index: 697253 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1185270 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5523. Min Act: -0.0000

Data Index: 183489 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1182365 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5261. Min Act: -0.0000

Data Index: 635450 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5218. Min Act: -0.0000

Data Index: 798005 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5547. Min Act: -0.0000

Data Index: 582012 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5124. Min Act: -0.0000

Data Index: 465333 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5014. Min Act: -0.0000

Data Index: 652676 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4866. Min Act: -0.0000

Data Index: 107224 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1051818 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5243. Min Act: -0.0000

Data Index: 208358 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4713. Min Act: -0.0000

Data Index: 969272 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4650. Min Act: -0.0000

Data Index: 219111 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1146836 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4606. Min Act: -0.0000

Data Index: 421975 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4715. Min Act: -0.0000

Data Index: 658278 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4861. Min Act: -0.0000

Data Index: 239065 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4534. Min Act: -0.0000

Data Index: 188864 (C4 (Web Text))

Max Activating Token Index: 424