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

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

Neuron 2504 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: 1.1927. Min Range: -1.1927

Max Act: 1.1927. Min Act: -0.0001

Data Index: 1311703 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8787. Min Act: -0.0001

Data Index: 1235993 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.9097. Min Act: -0.0001

Data Index: 128161 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8950. Min Act: -0.0001

Data Index: 496602 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8845. Min Act: -0.0001

Data Index: 334376 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.9127. Min Act: -0.0001

Data Index: 836668 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8371. Min Act: -0.0001

Data Index: 133929 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1134050 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.9056. Min Act: -0.0001

Data Index: 729769 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8684. Min Act: -0.0001

Data Index: 730940 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.7511. Min Act: -0.0001

Data Index: 692357 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8692. Min Act: -0.0001

Data Index: 469640 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8675. Min Act: -0.0001

Data Index: 553296 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.7838. Min Act: -0.0001

Data Index: 187071 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8190. Min Act: -0.0001

Data Index: 592292 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8441. Min Act: -0.0001

Data Index: 856744 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.8280. Min Act: -0.0001

Data Index: 940455 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.7935. Min Act: -0.0001

Data Index: 201372 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.7536. Min Act: -0.0001

Data Index: 979890 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 1.1927. Min Range: -1.1927

Max Act: 0.7758. Min Act: -0.0001

Data Index: 443719 (C4 (Web Text))

Max Activating Token Index: 958