Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 348 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1517130 (Python Code)

Max Activating Token Index: 269

Text #1

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1613760 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0639. Min Act: -0.0001

Data Index: 658569 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1341329 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0593. Min Act: -0.0001

Data Index: 81547 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0638. Min Act: -0.0001

Data Index: 812733 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0595. Min Act: -0.0001

Data Index: 351161 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0601. Min Act: -0.0001

Data Index: 729651 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0596. Min Act: -0.0001

Data Index: 899928 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0584. Min Act: -0.0001

Data Index: 149013 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0577. Min Act: -0.0001

Data Index: 356133 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0585. Min Act: -0.0001

Data Index: 938075 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0572. Min Act: -0.0001

Data Index: 510601 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0586. Min Act: -0.0001

Data Index: 5491 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0607. Min Act: -0.0001

Data Index: 730722 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1456682 (Python Code)

Max Activating Token Index: 779

Text #16

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0551. Min Act: -0.0001

Data Index: 238399 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1137731 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1278138 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0578. Min Act: -0.0001

Data Index: 502597 (C4 (Web Text))

Max Activating Token Index: 826