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

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

Neuron 3949 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: 1.8159. Min Range: -1.8159

Max Act: 1.6553. Min Act: -0.0000

Data Index: 15607 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.8159. Min Act: -0.0000

Data Index: 1606359 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.7711. Min Act: -0.0000

Data Index: 1481898 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.6620. Min Act: -0.0000

Data Index: 1649644 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.7210. Min Act: -0.0000

Data Index: 1559036 (Python Code)

Max Activating Token Index: 226

Text #5

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.7277. Min Act: -0.0000

Data Index: 453038 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5481. Min Act: -0.0000

Data Index: 1615850 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5077. Min Act: -0.0000

Data Index: 797394 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5845. Min Act: -0.0000

Data Index: 191904 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.3925. Min Act: -0.0000

Data Index: 1275896 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1517111 (Python Code)

Max Activating Token Index: 608

Text #11

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1586538 (Python Code)

Max Activating Token Index: 501

Text #12

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1044108 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5289. Min Act: -0.0000

Data Index: 123743 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5344. Min Act: -0.0000

Data Index: 880385 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.5834. Min Act: -0.0000

Data Index: 1538375 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.4926. Min Act: -0.0000

Data Index: 1611185 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.4954. Min Act: -0.0000

Data Index: 177708 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1589172 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 1.8159. Min Range: -1.8159

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1521314 (Python Code)

Max Activating Token Index: 394