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

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

Neuron 2132 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5418. Min Range: -2.5418

Max Act: 2.5418. Min Act: -0.0000

Data Index: 647732 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.7956. Min Act: -0.0001

Data Index: 903334 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.9341. Min Act: -0.0000

Data Index: 663432 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.9693. Min Act: -0.0000

Data Index: 892969 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.8183. Min Act: -0.0000

Data Index: 1183068 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.9078. Min Act: -0.0000

Data Index: 378858 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.8911. Min Act: -0.0000

Data Index: 234446 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.6842. Min Act: -0.0000

Data Index: 940350 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.7781. Min Act: -0.0000

Data Index: 687300 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.7692. Min Act: -0.0000

Data Index: 225350 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.7091. Min Act: -0.0000

Data Index: 831543 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.6821. Min Act: -0.0001

Data Index: 1313596 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.6807. Min Act: -0.0000

Data Index: 752611 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.6780. Min Act: -0.0000

Data Index: 291283 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.6580. Min Act: -0.0000

Data Index: 1093124 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.7017. Min Act: -0.0000

Data Index: 1264599 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.6085. Min Act: -0.0001

Data Index: 959984 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.7074. Min Act: -0.0000

Data Index: 535013 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.6848. Min Act: -0.0000

Data Index: 23569 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 2.5418. Min Range: -2.5418

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1224252 (C4 (Web Text))

Max Activating Token Index: 792