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

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

Neuron 2175 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: 4.1779. Min Range: -4.1779

Max Act: 4.1779. Min Act: -0.0000

Data Index: 1019264 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.4528. Min Act: -0.0000

Data Index: 165450 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.5743. Min Act: -0.0000

Data Index: 1300996 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.7034. Min Act: -0.0000

Data Index: 379182 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.9205. Min Act: -0.0000

Data Index: 813701 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.4364. Min Act: -0.0000

Data Index: 291883 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.7207. Min Act: -0.0000

Data Index: 885535 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.5572. Min Act: -0.0000

Data Index: 802718 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.3441. Min Act: -0.0000

Data Index: 787571 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.4950. Min Act: -0.0000

Data Index: 1256641 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.6317. Min Act: -0.0000

Data Index: 527345 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.3132. Min Act: -0.0000

Data Index: 741867 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.4013. Min Act: -0.0000

Data Index: 349654 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.3369. Min Act: -0.0000

Data Index: 664068 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.4677. Min Act: -0.0000

Data Index: 410124 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.1263. Min Act: -0.0000

Data Index: 1168857 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.1282. Min Act: -0.0000

Data Index: 824811 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.1780. Min Act: -0.0000

Data Index: 1038632 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.0690. Min Act: -0.0000

Data Index: 751874 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 4.1779. Min Range: -4.1779

Max Act: 3.0171. Min Act: -0.0000

Data Index: 450817 (C4 (Web Text))

Max Activating Token Index: 74