Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 682 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0447. Min Act: -0.0006

Data Index: 419988 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0426. Min Act: -0.0006

Data Index: 656761 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0404. Min Act: -0.0006

Data Index: 892420 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0389. Min Act: -0.0006

Data Index: 500009 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0412. Min Act: -0.0006

Data Index: 201635 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0379. Min Act: -0.0006

Data Index: 566512 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1055883 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0370. Min Act: -0.0006

Data Index: 237083 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0368. Min Act: -0.0006

Data Index: 679599 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0353. Min Act: -0.0006

Data Index: 207894 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0349. Min Act: -0.0006

Data Index: 392340 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0335. Min Act: -0.0006

Data Index: 494153 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0342. Min Act: -0.0006

Data Index: 729788 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1245198 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0357. Min Act: -0.0006

Data Index: 1017597 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0343. Min Act: -0.0006

Data Index: 857148 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0312. Min Act: -0.0006

Data Index: 879450 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0317. Min Act: -0.0006

Data Index: 824298 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0323. Min Act: -0.0006

Data Index: 804557 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0320. Min Act: -0.0006

Data Index: 971348 (C4 (Web Text))

Max Activating Token Index: 547