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

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

Neuron 2860 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1641531 (Python Code)

Max Activating Token Index: 279

Text #1

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1518381 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1471202 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1474124 (Python Code)

Max Activating Token Index: 204

Text #4

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7551. Min Act: 0.0000

Data Index: 1554767 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1614235 (Python Code)

Max Activating Token Index: 667

Text #6

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1440522 (Python Code)

Max Activating Token Index: 113

Text #7

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1530165 (Python Code)

Max Activating Token Index: 294

Text #8

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1471585 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1611785 (Python Code)

Max Activating Token Index: 958

Text #10

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1537322 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1616174 (Python Code)

Max Activating Token Index: 492

Text #12

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1551340 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1585160 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1506610 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1489159 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1372868 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5670. Min Act: 0.0000

Data Index: 1440636 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1562370 (Python Code)

Max Activating Token Index: 366

Text #19

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1416415 (Python Code)

Max Activating Token Index: 116