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

Dataset: The Pile

Neuron 4991 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: 5.9979. Min Range: -5.9979

Max Act: 5.7679. Min Act: -0.0000

Data Index: 878762 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 5.9979. Min Range: -5.9979

Max Act: 4.6844. Min Act: -0.0000

Data Index: 1439853 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.5381. Min Act: -0.0000

Data Index: 1468956 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 5.9979. Min Range: -5.9979

Max Act: 4.9829. Min Act: -0.0000

Data Index: 1037829 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.4944. Min Act: -0.0000

Data Index: 1253087 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.4777. Min Act: -0.0000

Data Index: 601653 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.9979. Min Act: -0.0000

Data Index: 1123767 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.2922. Min Act: -0.0000

Data Index: 375593 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.3197. Min Act: -0.0000

Data Index: 926302 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.9851. Min Act: -0.0000

Data Index: 96246 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.9619. Min Act: -0.0000

Data Index: 415118 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.2693. Min Act: -0.0000

Data Index: 719186 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.7476. Min Act: -0.0000

Data Index: 1895774 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.2418. Min Act: -0.0000

Data Index: 161603 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 5.9979. Min Range: -5.9979

Max Act: 4.9928. Min Act: -0.0000

Data Index: 191311 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.8277. Min Act: -0.0000

Data Index: 200125 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.8359. Min Act: -0.0000

Data Index: 290054 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.9724. Min Act: -0.0000

Data Index: 586469 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.8413. Min Act: -0.0000

Data Index: 1243674 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 5.9979. Min Range: -5.9979

Max Act: 5.8323. Min Act: -0.0000

Data Index: 1958922 (The Pile)

Max Activating Token Index: 477