Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3067 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0003

Data Index: 155242 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0316. Min Act: -0.0003

Data Index: 477705 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0302. Min Act: -0.0003

Data Index: 717379 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0287. Min Act: -0.0003

Data Index: 153642 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0285. Min Act: -0.0003

Data Index: 860389 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0296. Min Act: -0.0003

Data Index: 522164 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0285. Min Act: -0.0003

Data Index: 298932 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1321779 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1214265 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0280. Min Act: -0.0003

Data Index: 442182 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1252661 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0277. Min Act: -0.0003

Data Index: 928390 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0278. Min Act: -0.0003

Data Index: 611742 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0276. Min Act: -0.0003

Data Index: 612131 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1077055 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0249. Min Act: -0.0003

Data Index: 390604 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0266. Min Act: -0.0003

Data Index: 119840 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1092195 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1226904 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1280747 (C4 (Web Text))

Max Activating Token Index: 320