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

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

Neuron 1414 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0712. Min Act: -0.0002

Data Index: 369428 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0001

Data Index: 681344 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0623. Min Act: -0.0002

Data Index: 893468 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1641342 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1221834 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1029870 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0624. Min Act: -0.0002

Data Index: 35277 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1114666 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1397565 (Python Code)

Max Activating Token Index: 690

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0631. Min Act: -0.0002

Data Index: 732251 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1044034 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0573. Min Act: -0.0001

Data Index: 785309 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1009633 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0526. Min Act: -0.0001

Data Index: 702421 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1448421 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0517. Min Act: -0.0001

Data Index: 910249 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0553. Min Act: -0.0001

Data Index: 573441 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1237092 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0565. Min Act: -0.0002

Data Index: 996162 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1402743 (Python Code)

Max Activating Token Index: 180