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

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

Neuron 3713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.7187. Min Act: -0.0000

Data Index: 1136922 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.3948. Min Act: -0.0000

Data Index: 1353538 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.3583. Min Act: -0.0000

Data Index: 214970 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.9842. Min Act: -0.0000

Data Index: 592602 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.1087. Min Act: -0.0000

Data Index: 214186 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.4262. Min Act: -0.0000

Data Index: 660165 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.1719. Min Act: -0.0000

Data Index: 447389 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.1650. Min Act: -0.0000

Data Index: 1035201 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.1107. Min Act: -0.0000

Data Index: 693396 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.7852. Min Act: -0.0000

Data Index: 880428 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.8678. Min Act: -0.0000

Data Index: 383139 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.7109. Min Act: -0.0000

Data Index: 964287 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.8548. Min Act: -0.0000

Data Index: 336408 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 2.9842. Min Range: -2.9842

Max Act: 2.0705. Min Act: -0.0000

Data Index: 793222 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.7798. Min Act: -0.0000

Data Index: 964749 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.5871. Min Act: -0.0000

Data Index: 49958 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.7608. Min Act: -0.0000

Data Index: 36839 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.7530. Min Act: -0.0000

Data Index: 773243 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.2182. Min Act: -0.0000

Data Index: 859966 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 2.9842. Min Range: -2.9842

Max Act: 1.7021. Min Act: -0.0000

Data Index: 42849 (C4 (Web Text))

Max Activating Token Index: 69