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

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

Neuron 3676 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1725. Min Range: -2.1725

Max Act: 2.1725. Min Act: 0.0000

Data Index: 359469 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.9270. Min Act: -0.0000

Data Index: 1140428 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.9046. Min Act: -0.0000

Data Index: 630333 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.6698. Min Act: -0.0000

Data Index: 36777 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.7914. Min Act: 0.0000

Data Index: 463345 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.6634. Min Act: 0.0000

Data Index: 997758 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.6234. Min Act: -0.0000

Data Index: 1139691 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1315545 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1006462 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.5125. Min Act: -0.0000

Data Index: 1040854 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.5032. Min Act: -0.0000

Data Index: 508843 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1159246 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4721. Min Act: -0.0000

Data Index: 973189 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1260480 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1354425 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4643. Min Act: -0.0000

Data Index: 925385 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4571. Min Act: -0.0000

Data Index: 1173735 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4406. Min Act: -0.0000

Data Index: 92050 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4259. Min Act: -0.0000

Data Index: 709117 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 2.1725. Min Range: -2.1725

Max Act: 1.4294. Min Act: 0.0000

Data Index: 126302 (C4 (Web Text))

Max Activating Token Index: 838