Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3892 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.6237. Min Act: -0.0001

Data Index: 344114 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.3124. Min Act: -0.0001

Data Index: 595287 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1575. Min Act: -0.0001

Data Index: 61087 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2954. Min Act: -0.0001

Data Index: 165412 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1456. Min Act: -0.0001

Data Index: 1048465 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2729. Min Act: -0.0001

Data Index: 645367 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2042. Min Act: -0.0001

Data Index: 758017 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.3387. Min Act: -0.0001

Data Index: 883923 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1817. Min Act: -0.0001

Data Index: 830023 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1053. Min Act: -0.0001

Data Index: 477125 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1046. Min Act: -0.0001

Data Index: 335153 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1629. Min Act: -0.0001

Data Index: 921468 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2298. Min Act: -0.0001

Data Index: 1110131 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2401. Min Act: -0.0001

Data Index: 804960 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1197. Min Act: -0.0001

Data Index: 880491 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1689. Min Act: -0.0001

Data Index: 1940 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1310. Min Act: -0.0001

Data Index: 28750 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2780. Min Act: -0.0001

Data Index: 168161 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1355. Min Act: -0.0001

Data Index: 1079646 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1399. Min Act: -0.0001

Data Index: 798820 (C4 (Web Text))

Max Activating Token Index: 690