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

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

Neuron 4112 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1509208 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1519774 (Python Code)

Max Activating Token Index: 641

Text #2

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1386692 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1539733 (Python Code)

Max Activating Token Index: 784

Text #4

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1167. Min Act: -0.0002

Data Index: 1486094 (Python Code)

Max Activating Token Index: 601

Text #5

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1163. Min Act: -0.0002

Data Index: 714467 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1651165 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1555898 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1631529 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1367835 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1050. Min Act: -0.0002

Data Index: 601915 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1414610 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1399558 (Python Code)

Max Activating Token Index: 569

Text #13

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1650794 (Python Code)

Max Activating Token Index: 329

Text #14

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1429952 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1522067 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1608542 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0993. Min Act: -0.0002

Data Index: 834608 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1529447 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1583142 (Python Code)

Max Activating Token Index: 722