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

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

Neuron 1824 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0098. Min Range: -1.0098

Max Act: 1.0059. Min Act: -0.0000

Data Index: 684064 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.0098. Min Range: -1.0098

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1399962 (Python Code)

Max Activating Token Index: 752

Text #2

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1472662 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8808. Min Act: -0.0000

Data Index: 591060 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8348. Min Act: -0.0000

Data Index: 635484 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1386532 (Python Code)

Max Activating Token Index: 156

Text #6

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1524672 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8055. Min Act: -0.0000

Data Index: 854120 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1084608 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7850. Min Act: -0.0000

Data Index: 963849 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8050. Min Act: -0.0000

Data Index: 853775 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.9014. Min Act: -0.0000

Data Index: 368617 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8373. Min Act: -0.0000

Data Index: 935243 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.8274. Min Act: -0.0000

Data Index: 21275 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1444671 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7980. Min Act: -0.0000

Data Index: 278622 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1133434 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1009993 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7675. Min Act: -0.0000

Data Index: 175792 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.0098. Min Range: -1.0098

Max Act: 0.7543. Min Act: -0.0000

Data Index: 973252 (C4 (Web Text))

Max Activating Token Index: 87