Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2681 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1386989 (Python Code)

Max Activating Token Index: 661

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1443096 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0567. Min Act: -0.0002

Data Index: 433501 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1581684 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1578477 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1003651 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0421. Min Act: -0.0002

Data Index: 966158 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1044615 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1646147 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0406. Min Act: -0.0002

Data Index: 613341 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0389. Min Act: -0.0002

Data Index: 476781 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1243137 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0393. Min Act: -0.0002

Data Index: 756002 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1353965 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1048767 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1542131 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0371. Min Act: -0.0002

Data Index: 951556 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1022407 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1425832 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0363. Min Act: -0.0002

Data Index: 73744 (C4 (Web Text))

Max Activating Token Index: 784