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

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

Neuron 5188 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: 1.0672. Min Range: -1.0672

Max Act: 1.0672. Min Act: -0.0000

Data Index: 498773 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8965. Min Act: -0.0000

Data Index: 695350 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8281. Min Act: -0.0000

Data Index: 826456 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8430. Min Act: -0.0000

Data Index: 997451 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1089582 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1119162 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1030293 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1218944 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7455. Min Act: -0.0000

Data Index: 743000 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7002. Min Act: -0.0000

Data Index: 223332 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7248. Min Act: -0.0000

Data Index: 346152 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7141. Min Act: -0.0000

Data Index: 131527 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1376993 (Python Code)

Max Activating Token Index: 851

Text #13

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1063659 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1118909 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6725. Min Act: -0.0000

Data Index: 688003 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6638. Min Act: -0.0000

Data Index: 780699 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1270140 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6093. Min Act: -0.0000

Data Index: 539813 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6590. Min Act: -0.0000

Data Index: 150279 (C4 (Web Text))

Max Activating Token Index: 147