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

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

Neuron 706 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3589. Min Range: -1.3589

Max Act: 1.3589. Min Act: -0.0000

Data Index: 402969 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 1.3589. Min Range: -1.3589

Max Act: 1.2334. Min Act: -0.0000

Data Index: 709082 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.3589. Min Range: -1.3589

Max Act: 1.1861. Min Act: -0.0000

Data Index: 984328 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.3589. Min Range: -1.3589

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1598765 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9720. Min Act: -0.0000

Data Index: 288140 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1196788 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9447. Min Act: -0.0000

Data Index: 298360 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1076909 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9726. Min Act: -0.0000

Data Index: 216550 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1427311 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9894. Min Act: -0.0000

Data Index: 1155407 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.9344. Min Act: -0.0000

Data Index: 612204 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8983. Min Act: -0.0000

Data Index: 23735 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1118610 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8130. Min Act: -0.0000

Data Index: 780299 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1400149 (Python Code)

Max Activating Token Index: 222

Text #16

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8042. Min Act: -0.0000

Data Index: 634296 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1344865 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.8589. Min Act: -0.0000

Data Index: 49921 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.3589. Min Range: -1.3589

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1440672 (Python Code)

Max Activating Token Index: 475