Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1243 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0002

Data Index: 440757 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0976. Min Act: -0.0002

Data Index: 723740 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0900. Min Act: -0.0002

Data Index: 132470 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0919. Min Act: -0.0002

Data Index: 414448 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0950. Min Act: -0.0002

Data Index: 267434 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1008236 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1266233 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0906. Min Act: -0.0002

Data Index: 76484 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0902. Min Act: -0.0002

Data Index: 81887 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0897. Min Act: -0.0002

Data Index: 555719 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0894. Min Act: -0.0002

Data Index: 587785 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0929. Min Act: -0.0002

Data Index: 456445 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0894. Min Act: -0.0002

Data Index: 761947 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1180996 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0912. Min Act: -0.0002

Data Index: 58920 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0875. Min Act: -0.0002

Data Index: 11618 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1319125 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0902. Min Act: -0.0002

Data Index: 765440 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1335774 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0857. Min Act: -0.0002

Data Index: 972836 (C4 (Web Text))

Max Activating Token Index: 368