Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 897 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9002. Min Act: -0.0000

Data Index: 879065 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1731365 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9254. Min Act: -0.0000

Data Index: 773870 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1648454 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1950381 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1733644 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1724195 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8269. Min Act: -0.0000

Data Index: 369787 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1149863 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7916. Min Act: -0.0000

Data Index: 515012 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8748. Min Act: -0.0000

Data Index: 440888 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8008. Min Act: -0.0000

Data Index: 126411 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8820. Min Act: -0.0000

Data Index: 146687 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7475. Min Act: -0.0000

Data Index: 802747 (The Pile)

Max Activating Token Index: 917

Text #14

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1558055 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7669. Min Act: -0.0000

Data Index: 726840 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7762. Min Act: -0.0000

Data Index: 12935 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1386279 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1692500 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1585278 (The Pile)

Max Activating Token Index: 917