Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 205 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0003

Data Index: 496801 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0676. Min Act: -0.0003

Data Index: 952250 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0532. Min Act: -0.0004

Data Index: 224404 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1159590 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1287015 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0513. Min Act: -0.0004

Data Index: 1357695 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0505. Min Act: -0.0003

Data Index: 406450 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0500. Min Act: -0.0003

Data Index: 168597 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0491. Min Act: -0.0003

Data Index: 271315 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0480. Min Act: -0.0003

Data Index: 659230 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0480. Min Act: -0.0003

Data Index: 424848 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0490. Min Act: -0.0003

Data Index: 188620 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0484. Min Act: -0.0004

Data Index: 1111208 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0481. Min Act: -0.0003

Data Index: 997371 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0490. Min Act: -0.0004

Data Index: 1276421 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0470. Min Act: -0.0003

Data Index: 522725 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0470. Min Act: -0.0003

Data Index: 807510 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0464. Min Act: -0.0003

Data Index: 951706 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0455. Min Act: -0.0003

Data Index: 681971 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0464. Min Act: -0.0003

Data Index: 534934 (C4 (Web Text))

Max Activating Token Index: 781