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

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

Neuron 4520 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: 0.5391. Min Range: -0.5391

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1308309 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5203. Min Act: -0.0000

Data Index: 240954 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5391. Min Act: -0.0000

Data Index: 109977 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1158090 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5009. Min Act: -0.0000

Data Index: 574969 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5157. Min Act: -0.0000

Data Index: 814262 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1288349 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4956. Min Act: -0.0000

Data Index: 318998 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1608392 (Python Code)

Max Activating Token Index: 697

Text #9

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4765. Min Act: -0.0000

Data Index: 689036 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1163378 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1093410 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4898. Min Act: -0.0000

Data Index: 882196 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1006249 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4715. Min Act: -0.0000

Data Index: 55862 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1601838 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1020627 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4485. Min Act: -0.0000

Data Index: 979116 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1277447 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.5391. Min Range: -0.5391

Max Act: 0.4764. Min Act: -0.0000

Data Index: 995371 (C4 (Web Text))

Max Activating Token Index: 318