Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2534 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.5744. Min Act: -0.0000

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.0238. Min Act: -0.0000

Data Index: 567228 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.1428. Min Act: -0.0000

Data Index: 282667 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.0505. Min Act: -0.0000

Data Index: 671965 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.0347. Min Act: -0.0000

Data Index: 155693 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1545599 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1482967 (Python Code)

Max Activating Token Index: 463

Text #7

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9484. Min Act: -0.0000

Data Index: 48781 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.0730. Min Act: -0.0000

Data Index: 699979 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9900. Min Act: -0.0000

Data Index: 878463 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1370798 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9666. Min Act: -0.0000

Data Index: 848996 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9663. Min Act: -0.0000

Data Index: 97451 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9177. Min Act: -0.0000

Data Index: 706084 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.5744. Min Range: -1.5744

Max Act: 1.0204. Min Act: -0.0000

Data Index: 28910 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9379. Min Act: -0.0000

Data Index: 172389 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.9324. Min Act: -0.0000

Data Index: 63337 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.8656. Min Act: -0.0000

Data Index: 127093 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1486806 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 1.5744. Min Range: -1.5744

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1592508 (Python Code)

Max Activating Token Index: 1005