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

Dataset: The Pile

Neuron 1176 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: 0.6639. Min Range: -0.6639

Max Act: 0.6639. Min Act: -0.0000

Data Index: 510498 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5708. Min Act: -0.0000

Data Index: 115093 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5911. Min Act: -0.0000

Data Index: 912382 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1395629 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1875586 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1290024 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1085741 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1190166 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1532899 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5817. Min Act: -0.0000

Data Index: 312338 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5647. Min Act: -0.0000

Data Index: 108080 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1277751 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1219229 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5827. Min Act: -0.0000

Data Index: 802362 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1831379 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1027421 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1037427 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5340. Min Act: -0.0000

Data Index: 221327 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1068468 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5156. Min Act: -0.0000

Data Index: 227588 (The Pile)

Max Activating Token Index: 504