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

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

Neuron 2843 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3890. Min Act: -0.0001

Data Index: 1521787 (Python Code)

Max Activating Token Index: 396

Text #1

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3706. Min Act: -0.0001

Data Index: 884621 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3648. Min Act: -0.0001

Data Index: 1630513 (Python Code)

Max Activating Token Index: 1010

Text #3

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1081697 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3563. Min Act: -0.0001

Data Index: 1368707 (Python Code)

Max Activating Token Index: 76

Text #5

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3684. Min Act: -0.0000

Data Index: 614959 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3547. Min Act: -0.0000

Data Index: 453401 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3504. Min Act: -0.0001

Data Index: 956064 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3595. Min Act: -0.0001

Data Index: 1447333 (Python Code)

Max Activating Token Index: 962

Text #9

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3469. Min Act: -0.0001

Data Index: 1262796 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3717. Min Act: -0.0001

Data Index: 1654831 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1482280 (Python Code)

Max Activating Token Index: 170

Text #12

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3563. Min Act: -0.0001

Data Index: 1472611 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3427. Min Act: -0.0000

Data Index: 781738 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1442989 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3396. Min Act: -0.0001

Data Index: 737017 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3405. Min Act: -0.0001

Data Index: 622445 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3508. Min Act: -0.0001

Data Index: 249917 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3384. Min Act: -0.0001

Data Index: 548600 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3391. Min Act: -0.0001

Data Index: 1393626 (Python Code)

Max Activating Token Index: 97