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

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

Neuron 4889 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.7676. Min Act: -0.0000

Data Index: 490627 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.7495. Min Act: -0.0000

Data Index: 188702 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1125740 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.6435. Min Act: -0.0000

Data Index: 650933 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.6238. Min Act: -0.0000

Data Index: 16160 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5874. Min Act: -0.0000

Data Index: 604299 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5720. Min Act: -0.0000

Data Index: 683373 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5774. Min Act: -0.0000

Data Index: 170425 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5519. Min Act: -0.0000

Data Index: 453439 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5653. Min Act: -0.0000

Data Index: 87467 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1061708 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5435. Min Act: -0.0000

Data Index: 407071 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1266175 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1082520 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5022. Min Act: -0.0000

Data Index: 417024 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5097. Min Act: -0.0000

Data Index: 678778 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5091. Min Act: -0.0000

Data Index: 52532 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.4863. Min Act: -0.0000

Data Index: 372999 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5245. Min Act: -0.0000

Data Index: 396420 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.7676. Min Range: -0.7676

Max Act: 0.5067. Min Act: -0.0000

Data Index: 989435 (C4 (Web Text))

Max Activating Token Index: 389