Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 200 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0525. Min Act: -0.0001

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0000

Data Index: 500853 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0600. Min Act: -0.0001

Data Index: 903558 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0524. Min Act: -0.0000

Data Index: 379891 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0514. Min Act: -0.0000

Data Index: 48726 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0541. Min Act: -0.0001

Data Index: 627881 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0524. Min Act: -0.0000

Data Index: 56425 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0524. Min Act: -0.0000

Data Index: 497054 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1242181 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0506. Min Act: -0.0000

Data Index: 569132 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0475. Min Act: -0.0000

Data Index: 869059 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0468. Min Act: -0.0000

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0468. Min Act: -0.0001

Data Index: 1009125 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0363. Min Act: -0.0000

Data Index: 772076 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0472. Min Act: -0.0000

Data Index: 650730 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0462. Min Act: -0.0000

Data Index: 803399 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0446. Min Act: -0.0000

Data Index: 134189 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0452. Min Act: -0.0000

Data Index: 315344 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0474. Min Act: -0.0000

Data Index: 219432 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0480. Min Act: -0.0001

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 506