Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3223 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4052. Min Range: -2.4052

Max Act: 2.4052. Min Act: -0.0000

Data Index: 916410 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 2.4052. Min Range: -2.4052

Max Act: 2.3960. Min Act: -0.0000

Data Index: 282003 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 2.4052. Min Range: -2.4052

Max Act: 2.2955. Min Act: -0.0000

Data Index: 947960 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 2.4052. Min Range: -2.4052

Max Act: 2.1812. Min Act: -0.0000

Data Index: 189102 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 2.4052. Min Range: -2.4052

Max Act: 2.0237. Min Act: -0.0000

Data Index: 1063441 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.9900. Min Act: -0.0000

Data Index: 257887 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.8499. Min Act: -0.0000

Data Index: 706325 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.9439. Min Act: -0.0000

Data Index: 94146 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.7410. Min Act: -0.0000

Data Index: 450302 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.6590. Min Act: -0.0000

Data Index: 627231 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.7023. Min Act: -0.0000

Data Index: 1016654 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.5503. Min Act: -0.0000

Data Index: 265010 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1235494 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1121673 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1265574 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1194576 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1092025 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.5238. Min Act: -0.0000

Data Index: 578293 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1074535 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 2.4052. Min Range: -2.4052

Max Act: 1.4614. Min Act: -0.0000

Data Index: 840414 (C4 (Web Text))

Max Activating Token Index: 27