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

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

Neuron 5247 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: 4.6576. Min Range: -4.6576

Max Act: 4.6576. Min Act: -0.0000

Data Index: 307911 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 4.6576. Min Range: -4.6576

Max Act: 4.1864. Min Act: -0.0000

Data Index: 907995 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 4.6576. Min Range: -4.6576

Max Act: 3.2876. Min Act: -0.0000

Data Index: 482834 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 4.6576. Min Range: -4.6576

Max Act: 3.0844. Min Act: -0.0000

Data Index: 1227913 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.9762. Min Act: -0.0000

Data Index: 379799 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 4.6576. Min Range: -4.6576

Max Act: 3.0846. Min Act: -0.0000

Data Index: 817120 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 4.6576. Min Range: -4.6576

Max Act: 3.2959. Min Act: -0.0000

Data Index: 1239272 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.8863. Min Act: -0.0000

Data Index: 752566 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.9085. Min Act: -0.0000

Data Index: 1295709 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.7588. Min Act: -0.0000

Data Index: 165200 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.8322. Min Act: -0.0000

Data Index: 772961 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.7877. Min Act: -0.0000

Data Index: 808745 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.7344. Min Act: -0.0000

Data Index: 412682 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.5897. Min Act: -0.0000

Data Index: 363837 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.5226. Min Act: -0.0000

Data Index: 978332 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.6630. Min Act: -0.0000

Data Index: 1287197 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.6532. Min Act: -0.0000

Data Index: 675941 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.6407. Min Act: -0.0000

Data Index: 3850 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.7634. Min Act: -0.0000

Data Index: 1186620 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 4.6576. Min Range: -4.6576

Max Act: 2.6072. Min Act: -0.0000

Data Index: 632469 (C4 (Web Text))

Max Activating Token Index: 637