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

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

Neuron 1515 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.9158. Min Act: -0.0000

Data Index: 944658 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.8604. Min Act: -0.0000

Data Index: 670496 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.5367. Min Act: -0.0000

Data Index: 921806 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.4004. Min Act: -0.0000

Data Index: 261262 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2850. Min Act: -0.0000

Data Index: 910295 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2777. Min Act: -0.0000

Data Index: 579278 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2208. Min Act: -0.0000

Data Index: 370595 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1313468 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1685. Min Act: -0.0000

Data Index: 1114921 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2434. Min Act: -0.0000

Data Index: 722219 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2105. Min Act: -0.0000

Data Index: 781008 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1710. Min Act: -0.0000

Data Index: 800929 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2052. Min Act: -0.0000

Data Index: 741473 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2373. Min Act: -0.0000

Data Index: 874609 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1542. Min Act: -0.0000

Data Index: 790444 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1122147 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1901. Min Act: -0.0000

Data Index: 65264 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1400507 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1232009 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 1.9158. Min Range: -1.9158

Max Act: 1.2007. Min Act: -0.0000

Data Index: 846463 (C4 (Web Text))

Max Activating Token Index: 921