Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2575 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1121. Min Range: -1.1121

Max Act: 1.1121. Min Act: -0.0001

Data Index: 724558 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 1.1121. Min Range: -1.1121

Max Act: 1.0955. Min Act: -0.0001

Data Index: 1044517 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 1.1121. Min Range: -1.1121

Max Act: 1.0032. Min Act: -0.0001

Data Index: 936877 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9911. Min Act: -0.0001

Data Index: 374575 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.1121. Min Range: -1.1121

Max Act: 1.0421. Min Act: -0.0001

Data Index: 850323 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9448. Min Act: -0.0001

Data Index: 1180325 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9737. Min Act: -0.0001

Data Index: 333949 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9398. Min Act: -0.0001

Data Index: 872324 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 1.1121. Min Range: -1.1121

Max Act: 1.0299. Min Act: -0.0001

Data Index: 1090096 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.8955. Min Act: -0.0001

Data Index: 585248 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9675. Min Act: -0.0001

Data Index: 320244 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9344. Min Act: -0.0001

Data Index: 340148 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9467. Min Act: -0.0001

Data Index: 488439 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9237. Min Act: -0.0001

Data Index: 921471 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1189385 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9064. Min Act: -0.0001

Data Index: 200586 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9380. Min Act: -0.0001

Data Index: 1351599 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.9627. Min Act: -0.0001

Data Index: 1174334 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.8649. Min Act: -0.0001

Data Index: 245610 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.1121. Min Range: -1.1121

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1260872 (C4 (Web Text))

Max Activating Token Index: 769