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

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

Neuron 609 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5168. Min Range: -3.5168

Max Act: 3.5168. Min Act: -0.0000

Data Index: 1601930 (Python Code)

Max Activating Token Index: 296

Text #1

Max Range: 3.5168. Min Range: -3.5168

Max Act: 3.2478. Min Act: -0.0000

Data Index: 1630135 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.9256. Min Act: -0.0000

Data Index: 1452562 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.8448. Min Act: -0.0000

Data Index: 1491674 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.5908. Min Act: 0.0000

Data Index: 1368939 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.5371. Min Act: -0.0000

Data Index: 1540841 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.6091. Min Act: -0.0000

Data Index: 1487276 (Python Code)

Max Activating Token Index: 781

Text #7

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1638701 (Python Code)

Max Activating Token Index: 713

Text #8

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.5733. Min Act: -0.0000

Data Index: 1600263 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.3310. Min Act: -0.0000

Data Index: 1523162 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4649. Min Act: -0.0000

Data Index: 1455721 (Python Code)

Max Activating Token Index: 268

Text #11

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.5567. Min Act: -0.0000

Data Index: 1609384 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4522. Min Act: -0.0000

Data Index: 1556434 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4566. Min Act: -0.0000

Data Index: 1394132 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.5246. Min Act: -0.0000

Data Index: 1487404 (Python Code)

Max Activating Token Index: 961

Text #15

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4093. Min Act: -0.0000

Data Index: 1528316 (Python Code)

Max Activating Token Index: 453

Text #16

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.3856. Min Act: -0.0000

Data Index: 1585456 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.3659. Min Act: -0.0000

Data Index: 1419824 (Python Code)

Max Activating Token Index: 940

Text #18

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.4063. Min Act: -0.0000

Data Index: 1405248 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 3.5168. Min Range: -3.5168

Max Act: 2.2552. Min Act: -0.0000

Data Index: 1373589 (Python Code)

Max Activating Token Index: 482