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

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

Neuron 1520 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2889. Min Range: -1.2889

Max Act: 1.2889. Min Act: -0.0000

Data Index: 313938 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.2889. Min Range: -1.2889

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1054239 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.2889. Min Range: -1.2889

Max Act: 1.1817. Min Act: -0.0001

Data Index: 949525 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 1.2889. Min Range: -1.2889

Max Act: 1.0444. Min Act: -0.0000

Data Index: 913529 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 1.2889. Min Range: -1.2889

Max Act: 1.0424. Min Act: -0.0001

Data Index: 306315 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.2889. Min Range: -1.2889

Max Act: 1.0665. Min Act: -0.0000

Data Index: 86079 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.2889. Min Range: -1.2889

Max Act: 1.0438. Min Act: -0.0000

Data Index: 231487 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8919. Min Act: -0.0000

Data Index: 229439 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.9422. Min Act: -0.0001

Data Index: 283252 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8225. Min Act: -0.0001

Data Index: 471074 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.9016. Min Act: -0.0000

Data Index: 314537 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8289. Min Act: -0.0000

Data Index: 135506 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8871. Min Act: -0.0001

Data Index: 194552 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8973. Min Act: -0.0000

Data Index: 812333 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8913. Min Act: -0.0000

Data Index: 464716 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8318. Min Act: -0.0000

Data Index: 766348 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1081422 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8295. Min Act: -0.0001

Data Index: 809595 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.7992. Min Act: -0.0001

Data Index: 1091272 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.2889. Min Range: -1.2889

Max Act: 0.8300. Min Act: -0.0001

Data Index: 275945 (C4 (Web Text))

Max Activating Token Index: 812