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

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

Neuron 2170 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: 1.0645. Min Range: -1.0645

Max Act: 1.0318. Min Act: -0.0000

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1115315 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9684. Min Act: -0.0000

Data Index: 574986 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1068429 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0130. Min Act: -0.0000

Data Index: 57137 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1087940 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0056. Min Act: -0.0000

Data Index: 341487 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9552. Min Act: 0.0000

Data Index: 71362 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.0645. Min Range: -1.0645

Max Act: 1.0065. Min Act: -0.0000

Data Index: 826780 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9275. Min Act: -0.0000

Data Index: 320706 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9478. Min Act: -0.0000

Data Index: 543628 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8889. Min Act: -0.0000

Data Index: 724742 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9087. Min Act: -0.0000

Data Index: 542429 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9268. Min Act: -0.0000

Data Index: 849577 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9330. Min Act: -0.0000

Data Index: 119723 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9622. Min Act: -0.0000

Data Index: 786299 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9292. Min Act: 0.0000

Data Index: 394662 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.8899. Min Act: -0.0000

Data Index: 557706 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9334. Min Act: -0.0000

Data Index: 797789 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.0645. Min Range: -1.0645

Max Act: 0.9080. Min Act: -0.0000

Data Index: 276863 (C4 (Web Text))

Max Activating Token Index: 285