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

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

Neuron 1586 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.1498. Min Act: -0.0000

Data Index: 967282 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9622. Min Act: -0.0000

Data Index: 781120 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9884. Min Act: -0.0000

Data Index: 168581 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9975. Min Act: -0.0000

Data Index: 628472 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9369. Min Act: 0.0000

Data Index: 431857 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8606. Min Act: -0.0000

Data Index: 527405 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9146. Min Act: -0.0000

Data Index: 17676 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8740. Min Act: -0.0000

Data Index: 123482 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8703. Min Act: -0.0000

Data Index: 151445 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8655. Min Act: -0.0000

Data Index: 248233 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9053. Min Act: -0.0000

Data Index: 469514 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8224. Min Act: -0.0000

Data Index: 786735 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1268685 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8461. Min Act: -0.0000

Data Index: 768194 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8194. Min Act: -0.0000

Data Index: 371113 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1003740 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.7792. Min Act: -0.0000

Data Index: 777528 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1006915 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8463. Min Act: -0.0000

Data Index: 484774 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8272. Min Act: -0.0000

Data Index: 669414 (C4 (Web Text))

Max Activating Token Index: 563