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

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

Neuron 755 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: 0.1034. Min Range: -0.1034

Max Act: 0.1033. Min Act: -0.0002

Data Index: 743965 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.1034. Min Act: -0.0002

Data Index: 351500 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0887. Min Act: -0.0002

Data Index: 449926 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0911. Min Act: -0.0002

Data Index: 737329 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0867. Min Act: -0.0002

Data Index: 935581 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1081664 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0823. Min Act: -0.0002

Data Index: 203667 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1156239 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1646118 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0709. Min Act: -0.0002

Data Index: 704985 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0723. Min Act: -0.0002

Data Index: 506499 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1168517 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1582113 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0702. Min Act: -0.0002

Data Index: 333063 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0704. Min Act: -0.0002

Data Index: 299937 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1519520 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0725. Min Act: -0.0002

Data Index: 909166 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0723. Min Act: -0.0002

Data Index: 526354 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1268881 (C4 (Web Text))

Max Activating Token Index: 771