Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1174 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0003

Data Index: 296334 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1174287 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0685. Min Act: -0.0003

Data Index: 201517 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1057069 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0647. Min Act: -0.0003

Data Index: 134078 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1300618 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0647. Min Act: -0.0003

Data Index: 32148 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0627. Min Act: -0.0003

Data Index: 400337 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0610. Min Act: -0.0003

Data Index: 151057 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0654. Min Act: -0.0003

Data Index: 192356 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1178923 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1073984 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0579. Min Act: -0.0003

Data Index: 165431 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1204344 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0582. Min Act: -0.0003

Data Index: 518726 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0590. Min Act: -0.0003

Data Index: 205948 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0594. Min Act: -0.0003

Data Index: 839116 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1118187 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1022670 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1060239 (C4 (Web Text))

Max Activating Token Index: 922