Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 59 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1329617 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1103148 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1252314 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1147382 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0486. Min Act: -0.0002

Data Index: 585884 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0446. Min Act: -0.0002

Data Index: 642081 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0437. Min Act: -0.0002

Data Index: 739438 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0458. Min Act: -0.0002

Data Index: 225147 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0430. Min Act: -0.0001

Data Index: 241505 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0427. Min Act: -0.0002

Data Index: 110875 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0410. Min Act: -0.0002

Data Index: 598848 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0392. Min Act: -0.0002

Data Index: 730568 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1066519 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1328362 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0409. Min Act: -0.0002

Data Index: 517531 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0383. Min Act: -0.0002

Data Index: 761208 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1117260 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0403. Min Act: -0.0002

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1033262 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0413. Min Act: -0.0002

Data Index: 416548 (C4 (Web Text))

Max Activating Token Index: 596