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

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

Neuron 3706 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2317. Min Range: -3.2317

Max Act: 3.2317. Min Act: -0.0001

Data Index: 711952 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.9654. Min Act: -0.0001

Data Index: 396442 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.8463. Min Act: -0.0001

Data Index: 111732 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.9191. Min Act: -0.0001

Data Index: 379711 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.8523. Min Act: -0.0001

Data Index: 1042338 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.5115. Min Act: -0.0001

Data Index: 1238586 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.6225. Min Act: -0.0001

Data Index: 540477 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.5870. Min Act: -0.0001

Data Index: 554667 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.4039. Min Act: -0.0001

Data Index: 98519 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.2940. Min Act: -0.0001

Data Index: 706977 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.4700. Min Act: -0.0001

Data Index: 1050460 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.1033. Min Act: -0.0001

Data Index: 948352 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.2556. Min Act: -0.0001

Data Index: 170250 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.2240. Min Act: -0.0001

Data Index: 1221690 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.3079. Min Act: -0.0001

Data Index: 227012 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.1645. Min Act: -0.0001

Data Index: 1001523 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 3.2317. Min Range: -3.2317

Max Act: 1.9690. Min Act: -0.0001

Data Index: 115743 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.1810. Min Act: -0.0001

Data Index: 808932 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.4120. Min Act: -0.0001

Data Index: 1112497 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.2317. Min Range: -3.2317

Max Act: 2.1750. Min Act: -0.0001

Data Index: 884919 (C4 (Web Text))

Max Activating Token Index: 129