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

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

Neuron 433 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4895. Min Act: -0.0001

Data Index: 1543636 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1377027 (Python Code)

Max Activating Token Index: 216

Text #2

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1323950 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3723. Min Act: -0.0001

Data Index: 1579797 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1454850 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3936. Min Act: -0.0001

Data Index: 1410540 (Python Code)

Max Activating Token Index: 1012

Text #6

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3910. Min Act: -0.0000

Data Index: 806074 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1648319 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1652266 (Python Code)

Max Activating Token Index: 413

Text #9

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1433914 (Python Code)

Max Activating Token Index: 462

Text #10

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1454904 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3690. Min Act: -0.0001

Data Index: 1611623 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3678. Min Act: -0.0001

Data Index: 1524095 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3673. Min Act: -0.0001

Data Index: 1460874 (Python Code)

Max Activating Token Index: 813

Text #14

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3762. Min Act: -0.0001

Data Index: 1628640 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3504. Min Act: -0.0001

Data Index: 1629066 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1368842 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1515522 (Python Code)

Max Activating Token Index: 970

Text #18

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3443. Min Act: -0.0001

Data Index: 1449559 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3637. Min Act: -0.0001

Data Index: 1388965 (Python Code)

Max Activating Token Index: 66