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

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

Neuron 405 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: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0004

Data Index: 481134 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0530. Min Act: -0.0003

Data Index: 852175 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0525. Min Act: -0.0003

Data Index: 76629 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0517. Min Act: -0.0004

Data Index: 1252300 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0506. Min Act: -0.0003

Data Index: 79529 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0509. Min Act: -0.0003

Data Index: 434641 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1012642 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0515. Min Act: -0.0004

Data Index: 503329 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1244967 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1335100 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1368204 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0473. Min Act: -0.0004

Data Index: 230807 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1077336 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1207433 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1053668 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1465562 (Python Code)

Max Activating Token Index: 833

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0491. Min Act: -0.0003

Data Index: 707858 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1582288 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0461. Min Act: -0.0003

Data Index: 564208 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0442. Min Act: -0.0004

Data Index: 814214 (C4 (Web Text))

Max Activating Token Index: 762