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

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

Neuron 2787 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.2978. Min Act: -0.0001

Data Index: 411629 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0745. Min Act: -0.0001

Data Index: 1331664 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.0544. Min Act: -0.0001

Data Index: 520207 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1353. Min Act: -0.0001

Data Index: 141773 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 1.2978. Min Range: -1.2978

Max Act: 1.1137. Min Act: -0.0001

Data Index: 538326 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7770. Min Act: -0.0001

Data Index: 601540 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9299. Min Act: -0.0001

Data Index: 667318 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9431. Min Act: -0.0001

Data Index: 599344 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8973. Min Act: -0.0001

Data Index: 802444 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8588. Min Act: -0.0001

Data Index: 306309 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9509. Min Act: -0.0001

Data Index: 740474 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9106. Min Act: -0.0001

Data Index: 353466 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8781. Min Act: -0.0001

Data Index: 1195071 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9097. Min Act: -0.0001

Data Index: 1332174 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.7949. Min Act: -0.0001

Data Index: 1088169 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8613. Min Act: -0.0001

Data Index: 870314 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.9008. Min Act: -0.0001

Data Index: 246274 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8638. Min Act: -0.0001

Data Index: 410084 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1333096 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.2978. Min Range: -1.2978

Max Act: 0.8867. Min Act: -0.0001

Data Index: 708339 (C4 (Web Text))

Max Activating Token Index: 805