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

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

Neuron 1209 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: 0.0613. Min Range: -0.0613

Max Act: 0.0594. Min Act: -0.0002

Data Index: 256657 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0002

Data Index: 693808 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1146883 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0587. Min Act: -0.0002

Data Index: 422900 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0590. Min Act: -0.0002

Data Index: 933937 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0593. Min Act: -0.0002

Data Index: 39666 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0560. Min Act: -0.0002

Data Index: 252752 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0528. Min Act: -0.0002

Data Index: 220770 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0538. Min Act: -0.0002

Data Index: 349779 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0549. Min Act: -0.0002

Data Index: 57492 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0556. Min Act: -0.0002

Data Index: 392328 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0519. Min Act: -0.0002

Data Index: 72871 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0531. Min Act: -0.0002

Data Index: 221615 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1163252 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0491. Min Act: -0.0002

Data Index: 814657 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0501. Min Act: -0.0002

Data Index: 647055 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0511. Min Act: -0.0002

Data Index: 346191 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0500. Min Act: -0.0002

Data Index: 813518 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0510. Min Act: -0.0002

Data Index: 195340 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0521. Min Act: -0.0001

Data Index: 315447 (C4 (Web Text))

Max Activating Token Index: 497