Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 508 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0002

Data Index: 773157 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1067292 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1306522 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0450. Min Act: -0.0002

Data Index: 633017 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0432. Min Act: -0.0002

Data Index: 597462 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0424. Min Act: -0.0002

Data Index: 798546 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0439. Min Act: -0.0002

Data Index: 478610 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1429738 (Python Code)

Max Activating Token Index: 698

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1343717 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1153218 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0427. Min Act: -0.0002

Data Index: 94713 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0421. Min Act: -0.0001

Data Index: 116170 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0424. Min Act: -0.0002

Data Index: 354207 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0421. Min Act: -0.0002

Data Index: 103094 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0415. Min Act: -0.0002

Data Index: 83903 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0405. Min Act: -0.0002

Data Index: 860400 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0419. Min Act: -0.0003

Data Index: 892632 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0406. Min Act: -0.0002

Data Index: 581407 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1038124 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0391. Min Act: -0.0003

Data Index: 736260 (C4 (Web Text))

Max Activating Token Index: 605