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

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

Neuron 2672 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0002

Data Index: 213828 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0745. Min Act: -0.0002

Data Index: 763517 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0642. Min Act: -0.0002

Data Index: 92851 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0633. Min Act: -0.0002

Data Index: 484936 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0646. Min Act: -0.0002

Data Index: 138036 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1181005 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0624. Min Act: -0.0002

Data Index: 901170 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1202382 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1291241 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1197378 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0592. Min Act: -0.0002

Data Index: 234466 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0592. Min Act: -0.0002

Data Index: 307651 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1186280 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0580. Min Act: -0.0002

Data Index: 266444 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0569. Min Act: -0.0002

Data Index: 693534 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0565. Min Act: -0.0002

Data Index: 130331 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0567. Min Act: -0.0002

Data Index: 998207 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0562. Min Act: -0.0002

Data Index: 889042 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1172351 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1311322 (C4 (Web Text))

Max Activating Token Index: 368