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

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

Neuron 2522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.5659. Min Act: -0.0001

Data Index: 151478 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.4183. Min Act: -0.0000

Data Index: 1034522 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.3651. Min Act: -0.0001

Data Index: 583050 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2227. Min Act: -0.0001

Data Index: 887761 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.3293. Min Act: -0.0001

Data Index: 173210 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.3158. Min Act: -0.0001

Data Index: 1058443 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.3458. Min Act: -0.0001

Data Index: 1174408 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2428. Min Act: -0.0001

Data Index: 1118193 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2267. Min Act: -0.0000

Data Index: 406314 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2620. Min Act: -0.0001

Data Index: 1028129 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1970. Min Act: -0.0000

Data Index: 600475 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1682. Min Act: -0.0001

Data Index: 633557 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2634. Min Act: -0.0001

Data Index: 1002976 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2254. Min Act: -0.0001

Data Index: 438279 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2300. Min Act: -0.0001

Data Index: 300026 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1835. Min Act: -0.0000

Data Index: 634519 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.2805. Min Act: -0.0001

Data Index: 602151 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1430. Min Act: -0.0001

Data Index: 1227306 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1172. Min Act: -0.0001

Data Index: 1319001 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.5659. Min Range: -1.5659

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1236396 (C4 (Web Text))

Max Activating Token Index: 214