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

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

Neuron 3947 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0062. Min Range: -2.0062

Max Act: 2.0062. Min Act: -0.0000

Data Index: 277632 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.8590. Min Act: -0.0000

Data Index: 1302213 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.9055. Min Act: -0.0000

Data Index: 530020 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.8724. Min Act: -0.0001

Data Index: 1272644 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.8471. Min Act: -0.0000

Data Index: 914076 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.8467. Min Act: -0.0000

Data Index: 925385 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.8262. Min Act: -0.0000

Data Index: 959879 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.9035. Min Act: -0.0000

Data Index: 1033872 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.9872. Min Act: -0.0000

Data Index: 237666 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.5900. Min Act: -0.0000

Data Index: 377851 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.8291. Min Act: -0.0000

Data Index: 448820 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.6077. Min Act: -0.0000

Data Index: 398587 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.5150. Min Act: -0.0000

Data Index: 94553 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.5757. Min Act: -0.0000

Data Index: 732913 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.6131. Min Act: -0.0000

Data Index: 1209656 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.7408. Min Act: -0.0000

Data Index: 899491 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.4882. Min Act: -0.0000

Data Index: 437291 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.4737. Min Act: -0.0001

Data Index: 833858 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.4277. Min Act: -0.0000

Data Index: 128876 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 2.0062. Min Range: -2.0062

Max Act: 1.6056. Min Act: -0.0000

Data Index: 204264 (C4 (Web Text))

Max Activating Token Index: 24