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

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

Neuron 1366 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.7172. Min Act: -0.0000

Data Index: 1441674 (Python Code)

Max Activating Token Index: 777

Text #1

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.6645. Min Act: -0.0000

Data Index: 1432353 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1627322 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1381780 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1540926 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1383794 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1530505 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1488840 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1449669 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.4638. Min Act: -0.0000

Data Index: 1384707 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1444933 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1639883 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1379442 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1415392 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1617220 (Python Code)

Max Activating Token Index: 334

Text #15

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.2708. Min Act: -0.0000

Data Index: 1506179 (Python Code)

Max Activating Token Index: 233

Text #16

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.4015. Min Act: -0.0000

Data Index: 1435998 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1531897 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1473481 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 1.7172. Min Range: -1.7172

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1403527 (Python Code)

Max Activating Token Index: 1018