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

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

Neuron 1916 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: 0.0692. Min Range: -0.0692

Max Act: 0.0692. Min Act: -0.0003

Data Index: 344298 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1296842 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1288570 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0630. Min Act: -0.0003

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0533. Min Act: -0.0003

Data Index: 461725 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1088610 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0565. Min Act: -0.0003

Data Index: 666821 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0550. Min Act: -0.0002

Data Index: 603328 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1184552 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1235079 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0545. Min Act: -0.0003

Data Index: 487216 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0542. Min Act: -0.0003

Data Index: 635486 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0534. Min Act: -0.0003

Data Index: 757130 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0512. Min Act: -0.0003

Data Index: 639364 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0507. Min Act: -0.0003

Data Index: 91871 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0544. Min Act: -0.0003

Data Index: 650096 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1083801 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0538. Min Act: -0.0004

Data Index: 808187 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0523. Min Act: -0.0003

Data Index: 5165 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0500. Min Act: -0.0003

Data Index: 646293 (C4 (Web Text))

Max Activating Token Index: 237