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

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

Neuron 29 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0006

Data Index: 111782 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1082653 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0525. Min Act: -0.0006

Data Index: 1118042 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0526. Min Act: -0.0006

Data Index: 452229 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0510. Min Act: -0.0006

Data Index: 631970 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0488. Min Act: -0.0006

Data Index: 151515 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0503. Min Act: -0.0006

Data Index: 657018 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0504. Min Act: -0.0006

Data Index: 938135 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0502. Min Act: -0.0006

Data Index: 991842 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0507. Min Act: -0.0006

Data Index: 746011 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0505. Min Act: -0.0006

Data Index: 948192 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1342034 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0505. Min Act: -0.0006

Data Index: 919333 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0504. Min Act: -0.0006

Data Index: 121959 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0481. Min Act: -0.0006

Data Index: 836346 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0490. Min Act: -0.0006

Data Index: 510225 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0487. Min Act: -0.0006

Data Index: 736645 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0476. Min Act: -0.0006

Data Index: 1205394 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0475. Min Act: -0.0006

Data Index: 211350 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0486. Min Act: -0.0006

Data Index: 413795 (C4 (Web Text))

Max Activating Token Index: 392