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

Dataset: The Pile

Neuron 3088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1272641 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3809. Min Act: -0.0000

Data Index: 399858 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1773798 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3100. Min Act: -0.0000

Data Index: 4353 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3129. Min Act: -0.0000

Data Index: 364 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2854. Min Act: -0.0000

Data Index: 739140 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3324. Min Act: -0.0000

Data Index: 816034 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2054. Min Act: -0.0001

Data Index: 1278180 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1521326 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2557. Min Act: -0.0000

Data Index: 535244 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1245978 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2442. Min Act: -0.0000

Data Index: 345054 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1458127 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1596496 (The Pile)

Max Activating Token Index: 780

Text #14

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1217709 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1411141 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2423. Min Act: -0.0000

Data Index: 601802 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2027. Min Act: -0.0000

Data Index: 24505 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2611. Min Act: -0.0000

Data Index: 79193 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.2140. Min Act: -0.0000

Data Index: 470256 (The Pile)

Max Activating Token Index: 1009