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

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

Neuron 3181 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0003

Data Index: 34630 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0655. Min Act: -0.0003

Data Index: 862653 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1308163 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0580. Min Act: -0.0003

Data Index: 122864 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0567. Min Act: -0.0003

Data Index: 606571 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0537. Min Act: -0.0003

Data Index: 119657 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0518. Min Act: -0.0004

Data Index: 550355 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0511. Min Act: -0.0003

Data Index: 775493 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0507. Min Act: -0.0003

Data Index: 216625 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0508. Min Act: -0.0003

Data Index: 301241 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0510. Min Act: -0.0003

Data Index: 677785 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0531. Min Act: -0.0003

Data Index: 445879 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1232623 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1250426 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0499. Min Act: -0.0003

Data Index: 59117 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0520. Min Act: -0.0003

Data Index: 950320 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0553. Min Act: -0.0003

Data Index: 810797 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0426. Min Act: -0.0003

Data Index: 485865 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1206560 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0508. Min Act: -0.0003

Data Index: 223498 (C4 (Web Text))

Max Activating Token Index: 717