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

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

Neuron 4434 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: 0.0617. Min Range: -0.0617

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1220289 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1010259 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0509. Min Act: -0.0000

Data Index: 967620 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1102214 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0322. Min Act: -0.0000

Data Index: 813988 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0318. Min Act: -0.0000

Data Index: 542443 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0321. Min Act: -0.0000

Data Index: 573956 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0299. Min Act: -0.0000

Data Index: 252005 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0310. Min Act: -0.0000

Data Index: 559537 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0289. Min Act: -0.0000

Data Index: 224302 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0211. Min Act: -0.0000

Data Index: 889378 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0254. Min Act: -0.0000

Data Index: 205697 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1432755 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1112480 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0258. Min Act: -0.0000

Data Index: 969750 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0251. Min Act: -0.0000

Data Index: 725170 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0264. Min Act: -0.0000

Data Index: 48455 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0240. Min Act: -0.0000

Data Index: 1230261 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0242. Min Act: -0.0000

Data Index: 1041735 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0247. Min Act: -0.0001

Data Index: 982205 (C4 (Web Text))

Max Activating Token Index: 731