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

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

Neuron 2012 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0566. Min Act: -0.0005

Data Index: 567890 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0537. Min Act: -0.0005

Data Index: 1320953 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0497. Min Act: -0.0005

Data Index: 905933 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0496. Min Act: -0.0005

Data Index: 1220553 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0435. Min Act: -0.0005

Data Index: 163954 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0480. Min Act: -0.0005

Data Index: 930322 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1102686 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0439. Min Act: -0.0005

Data Index: 58407 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0431. Min Act: -0.0005

Data Index: 755197 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0406. Min Act: -0.0005

Data Index: 1035647 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0434. Min Act: -0.0005

Data Index: 1187485 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0417. Min Act: -0.0005

Data Index: 48198 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0421. Min Act: -0.0005

Data Index: 17208 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0410. Min Act: -0.0005

Data Index: 973798 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0399. Min Act: -0.0005

Data Index: 192140 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0399. Min Act: -0.0005

Data Index: 849928 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0418. Min Act: -0.0005

Data Index: 982755 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0434. Min Act: -0.0005

Data Index: 892951 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0417. Min Act: -0.0005

Data Index: 851665 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0566. Min Range: -0.0566

Max Act: 0.0405. Min Act: -0.0005

Data Index: 1042237 (C4 (Web Text))

Max Activating Token Index: 377