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

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

Neuron 1675 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: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1037701 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0510. Min Act: -0.0002

Data Index: 141063 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0548. Min Act: -0.0002

Data Index: 256758 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0457. Min Act: -0.0002

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1236152 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0448. Min Act: -0.0002

Data Index: 468228 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0413. Min Act: -0.0001

Data Index: 504044 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0401. Min Act: -0.0002

Data Index: 99806 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0415. Min Act: -0.0002

Data Index: 684347 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0416. Min Act: -0.0002

Data Index: 935709 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0410. Min Act: -0.0002

Data Index: 434252 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0421. Min Act: -0.0002

Data Index: 126822 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0354. Min Act: -0.0001

Data Index: 782895 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1105462 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1048050 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0366. Min Act: -0.0002

Data Index: 449552 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0448. Min Act: -0.0002

Data Index: 582336 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0334. Min Act: -0.0002

Data Index: 637310 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0319. Min Act: -0.0002

Data Index: 572182 (C4 (Web Text))

Max Activating Token Index: 777