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

Dataset: The Pile

Neuron 4221 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: 5.2353. Min Range: -5.2353

Max Act: 4.9304. Min Act: -0.0000

Data Index: 548236 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 5.2353. Min Range: -5.2353

Max Act: 5.2353. Min Act: -0.0000

Data Index: 150842 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 5.2353. Min Range: -5.2353

Max Act: 4.5806. Min Act: -0.0000

Data Index: 1084446 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 5.2353. Min Range: -5.2353

Max Act: 4.1993. Min Act: -0.0000

Data Index: 685700 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 5.2353. Min Range: -5.2353

Max Act: 4.3452. Min Act: -0.0000

Data Index: 1831922 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.8807. Min Act: -0.0000

Data Index: 542083 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.8318. Min Act: -0.0000

Data Index: 808173 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.7558. Min Act: -0.0000

Data Index: 1559575 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.3199. Min Act: -0.0000

Data Index: 661624 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.8033. Min Act: -0.0000

Data Index: 531716 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 5.2353. Min Range: -5.2353

Max Act: 2.7322. Min Act: -0.0000

Data Index: 716837 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.3970. Min Act: -0.0000

Data Index: 1225346 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.1760. Min Act: -0.0000

Data Index: 1633663 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.1868. Min Act: -0.0000

Data Index: 1148422 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 5.2353. Min Range: -5.2353

Max Act: 2.9988. Min Act: -0.0000

Data Index: 124999 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 5.2353. Min Range: -5.2353

Max Act: 2.9350. Min Act: -0.0000

Data Index: 1576761 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 5.2353. Min Range: -5.2353

Max Act: 3.0737. Min Act: -0.0000

Data Index: 1004019 (The Pile)

Max Activating Token Index: 873

Text #17

Max Range: 5.2353. Min Range: -5.2353

Max Act: 2.6460. Min Act: -0.0000

Data Index: 955933 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 5.2353. Min Range: -5.2353

Max Act: 2.7593. Min Act: -0.0000

Data Index: 1263886 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 5.2353. Min Range: -5.2353

Max Act: 2.9973. Min Act: -0.0000

Data Index: 1367775 (The Pile)

Max Activating Token Index: 367