Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 736 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.5033. Min Act: -0.0000

Data Index: 365365 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1550290 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1996121 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4229. Min Act: -0.0000

Data Index: 118672 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3801. Min Act: -0.0000

Data Index: 295803 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3827. Min Act: -0.0000

Data Index: 215728 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1656345 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3738. Min Act: -0.0000

Data Index: 377554 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1130091 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1714604 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1720362 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3422. Min Act: -0.0000

Data Index: 175786 (The Pile)

Max Activating Token Index: 831

Text #12

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1116232 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1076909 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1759994 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1339785 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3614. Min Act: -0.0001

Data Index: 1057085 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3252. Min Act: -0.0000

Data Index: 150679 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3452. Min Act: -0.0000

Data Index: 261155 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1818788 (The Pile)

Max Activating Token Index: 818