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

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

Neuron 2029 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.8428. Min Act: -0.0000

Data Index: 754338 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.6842. Min Act: -0.0000

Data Index: 284192 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1199455 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1042918 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.2579. Min Act: -0.0000

Data Index: 100477 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.2006. Min Act: -0.0000

Data Index: 580327 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1269796 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.1449. Min Act: -0.0000

Data Index: 976496 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.1095. Min Act: -0.0000

Data Index: 862610 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.1020. Min Act: -0.0000

Data Index: 197953 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.0624. Min Act: -0.0000

Data Index: 809604 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.0567. Min Act: 0.0000

Data Index: 843476 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.0513. Min Act: -0.0000

Data Index: 531057 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.0411. Min Act: -0.0000

Data Index: 749429 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.8428. Min Range: -1.8428

Max Act: 0.9787. Min Act: 0.0000

Data Index: 652187 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.0664. Min Act: -0.0000

Data Index: 66342 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1160516 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 1.8428. Min Range: -1.8428

Max Act: 1.0775. Min Act: -0.0000

Data Index: 273222 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.8428. Min Range: -1.8428

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1067711 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 1.8428. Min Range: -1.8428

Max Act: 0.9695. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 779