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

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

Neuron 3812 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: 4.0639. Min Range: -4.0639

Max Act: 4.0639. Min Act: -0.0000

Data Index: 980133 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 4.0639. Min Range: -4.0639

Max Act: 3.1648. Min Act: -0.0000

Data Index: 1107030 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 4.0639. Min Range: -4.0639

Max Act: 3.1034. Min Act: -0.0000

Data Index: 879507 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.7860. Min Act: -0.0000

Data Index: 1301868 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.6115. Min Act: -0.0000

Data Index: 1044862 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.6055. Min Act: -0.0000

Data Index: 507334 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.5596. Min Act: -0.0000

Data Index: 135798 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.6508. Min Act: -0.0000

Data Index: 1227101 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.5187. Min Act: -0.0000

Data Index: 266775 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.3803. Min Act: -0.0000

Data Index: 1244845 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.3784. Min Act: -0.0000

Data Index: 310803 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.4419. Min Act: -0.0000

Data Index: 172220 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.3297. Min Act: -0.0000

Data Index: 594505 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.3349. Min Act: -0.0000

Data Index: 660730 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.3792. Min Act: -0.0000

Data Index: 794907 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.5010. Min Act: -0.0000

Data Index: 1099063 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.2962. Min Act: -0.0000

Data Index: 1021091 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.3286. Min Act: -0.0000

Data Index: 441139 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.3089. Min Act: -0.0000

Data Index: 51140 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 4.0639. Min Range: -4.0639

Max Act: 2.2968. Min Act: -0.0000

Data Index: 521356 (C4 (Web Text))

Max Activating Token Index: 64