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

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

Neuron 2229 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: 1.0068. Min Range: -1.0068

Max Act: 1.0068. Min Act: -0.0003

Data Index: 1626973 (Python Code)

Max Activating Token Index: 773

Text #1

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8438. Min Act: -0.0003

Data Index: 1510151 (Python Code)

Max Activating Token Index: 260

Text #2

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.8404. Min Act: -0.0003

Data Index: 1644683 (Python Code)

Max Activating Token Index: 760

Text #3

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7856. Min Act: -0.0003

Data Index: 1423760 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7163. Min Act: -0.0003

Data Index: 1513282 (Python Code)

Max Activating Token Index: 662

Text #5

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7299. Min Act: -0.0003

Data Index: 1422237 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7485. Min Act: -0.0003

Data Index: 1605591 (Python Code)

Max Activating Token Index: 391

Text #7

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6817. Min Act: -0.0003

Data Index: 1600679 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7183. Min Act: -0.0003

Data Index: 1410370 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7027. Min Act: -0.0003

Data Index: 1419720 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6796. Min Act: -0.0003

Data Index: 1596316 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6550. Min Act: -0.0003

Data Index: 1476712 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6809. Min Act: -0.0003

Data Index: 1565151 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6365. Min Act: -0.0003

Data Index: 1421905 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6498. Min Act: -0.0003

Data Index: 1481202 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6267. Min Act: -0.0003

Data Index: 1441454 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6181. Min Act: -0.0002

Data Index: 1602717 (Python Code)

Max Activating Token Index: 746

Text #17

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6161. Min Act: -0.0003

Data Index: 1447838 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5973. Min Act: -0.0003

Data Index: 1544547 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5923. Min Act: -0.0003

Data Index: 1486437 (Python Code)

Max Activating Token Index: 380