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

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

Neuron 2723 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.9659. Min Act: -0.0003

Data Index: 753070 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.8034. Min Act: -0.0003

Data Index: 1043168 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.7292. Min Act: -0.0003

Data Index: 443050 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.7597. Min Act: -0.0003

Data Index: 349898 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6731. Min Act: -0.0003

Data Index: 240831 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6706. Min Act: -0.0003

Data Index: 1243226 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.7402. Min Act: -0.0003

Data Index: 1327695 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6774. Min Act: -0.0003

Data Index: 788665 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6879. Min Act: -0.0003

Data Index: 632102 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6732. Min Act: -0.0003

Data Index: 992749 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6635. Min Act: -0.0003

Data Index: 275881 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6522. Min Act: -0.0003

Data Index: 1035600 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6576. Min Act: -0.0003

Data Index: 126447 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6247. Min Act: -0.0003

Data Index: 951016 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6272. Min Act: -0.0003

Data Index: 1295404 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6658. Min Act: -0.0003

Data Index: 495308 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6657. Min Act: -0.0003

Data Index: 954393 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6414. Min Act: -0.0003

Data Index: 1285747 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.5664. Min Act: -0.0003

Data Index: 706438 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.9659. Min Range: -0.9659

Max Act: 0.6403. Min Act: -0.0003

Data Index: 817578 (C4 (Web Text))

Max Activating Token Index: 48