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

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

Neuron 4408 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0733. Min Act: -0.0001

Data Index: 500991 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0712. Min Act: -0.0001

Data Index: 112372 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1172661 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0621. Min Act: -0.0001

Data Index: 558754 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0643. Min Act: -0.0002

Data Index: 664619 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0580. Min Act: -0.0001

Data Index: 726210 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0595. Min Act: -0.0001

Data Index: 399173 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0613. Min Act: -0.0001

Data Index: 133613 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0596. Min Act: -0.0001

Data Index: 657193 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1013258 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1129072 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1183107 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0569. Min Act: -0.0001

Data Index: 62295 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0569. Min Act: -0.0001

Data Index: 156653 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0571. Min Act: -0.0001

Data Index: 696676 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0591. Min Act: -0.0001

Data Index: 213404 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0547. Min Act: -0.0001

Data Index: 539270 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1279433 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0532. Min Act: -0.0001

Data Index: 177483 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1208042 (C4 (Web Text))

Max Activating Token Index: 154