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

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

Neuron 934 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: 1.9871. Min Range: -1.9871

Max Act: 1.9128. Min Act: -0.0000

Data Index: 558017 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.9871. Min Act: -0.0000

Data Index: 1214091 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.9567. Min Act: -0.0000

Data Index: 339251 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.9283. Min Act: -0.0000

Data Index: 1237148 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.8942. Min Act: -0.0000

Data Index: 861038 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.8941. Min Act: -0.0000

Data Index: 312993 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1255442 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.8719. Min Act: -0.0000

Data Index: 959484 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.8138. Min Act: -0.0000

Data Index: 14675 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.6142. Min Act: -0.0000

Data Index: 1302213 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.8886. Min Act: -0.0000

Data Index: 1212838 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.6587. Min Act: -0.0000

Data Index: 421924 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.6336. Min Act: -0.0000

Data Index: 470266 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.8212. Min Act: -0.0000

Data Index: 948025 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.7156. Min Act: -0.0000

Data Index: 435795 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.6911. Min Act: -0.0000

Data Index: 1339229 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.6823. Min Act: -0.0000

Data Index: 868208 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.5705. Min Act: -0.0000

Data Index: 751258 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.6662. Min Act: -0.0000

Data Index: 977985 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 1.9871. Min Range: -1.9871

Max Act: 1.6597. Min Act: -0.0000

Data Index: 1271054 (C4 (Web Text))

Max Activating Token Index: 759