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

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

Neuron 249 in Layer 1

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: -0.0006

Data Index: 998651 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0755. Min Act: -0.0006

Data Index: 116300 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0762. Min Act: -0.0006

Data Index: 1103251 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0738. Min Act: -0.0006

Data Index: 240824 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0715. Min Act: -0.0006

Data Index: 305923 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0680. Min Act: -0.0006

Data Index: 1328552 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0673. Min Act: -0.0006

Data Index: 451615 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0685. Min Act: -0.0006

Data Index: 247381 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0696. Min Act: -0.0006

Data Index: 272866 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0682. Min Act: -0.0006

Data Index: 442122 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0680. Min Act: -0.0006

Data Index: 450242 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0675. Min Act: -0.0006

Data Index: 1000397 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0647. Min Act: -0.0006

Data Index: 733257 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0659. Min Act: -0.0006

Data Index: 271954 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0681. Min Act: -0.0006

Data Index: 695581 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0667. Min Act: -0.0006

Data Index: 1243609 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0666. Min Act: -0.0006

Data Index: 531345 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0678. Min Act: -0.0006

Data Index: 422215 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0650. Min Act: -0.0006

Data Index: 1017178 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0635. Min Act: -0.0006

Data Index: 536704 (C4 (Web Text))

Max Activating Token Index: 373