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

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

Neuron 3114 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.7952. Min Act: -0.0000

Data Index: 1411103 (Python Code)

Max Activating Token Index: 276

Text #1

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.8294. Min Act: -0.0000

Data Index: 1545991 (Python Code)

Max Activating Token Index: 938

Text #2

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.5933. Min Act: -0.0000

Data Index: 1384887 (Python Code)

Max Activating Token Index: 136

Text #3

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.5690. Min Act: -0.0000

Data Index: 1379295 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.5736. Min Act: -0.0000

Data Index: 1479384 (Python Code)

Max Activating Token Index: 420

Text #5

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.6147. Min Act: -0.0000

Data Index: 1493937 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.4630. Min Act: -0.0000

Data Index: 1495788 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.3093. Min Act: -0.0000

Data Index: 1426099 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.3006. Min Act: -0.0000

Data Index: 1395008 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.1662. Min Act: -0.0000

Data Index: 1597014 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.3086. Min Act: -0.0000

Data Index: 1519999 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.2729. Min Act: -0.0000

Data Index: 1394061 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.1290. Min Act: -0.0000

Data Index: 1509466 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.3712. Min Act: -0.0000

Data Index: 1479800 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1497248 (Python Code)

Max Activating Token Index: 664

Text #15

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.2811. Min Act: -0.0000

Data Index: 1479733 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.0297. Min Act: -0.0000

Data Index: 1425102 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.1185. Min Act: -0.0000

Data Index: 1600817 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.0199. Min Act: -0.0000

Data Index: 1389500 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 2.8294. Min Range: -2.8294

Max Act: 2.1088. Min Act: -0.0000

Data Index: 1603341 (Python Code)

Max Activating Token Index: 708