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

Dataset: The Pile

Neuron 3523 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.1600. Min Act: -0.0000

Data Index: 930522 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.1593. Min Act: -0.0000

Data Index: 141583 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9218. Min Act: -0.0000

Data Index: 407255 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1020188 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9591. Min Act: -0.0000

Data Index: 593240 (The Pile)

Max Activating Token Index: 764

Text #5

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9361. Min Act: -0.0000

Data Index: 368323 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9365. Min Act: -0.0000

Data Index: 386063 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1238480 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9017. Min Act: -0.0000

Data Index: 601367 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1123295 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8581. Min Act: -0.0000

Data Index: 253362 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1792919 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1919148 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1596322 (The Pile)

Max Activating Token Index: 387

Text #14

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7609. Min Act: -0.0000

Data Index: 438715 (The Pile)

Max Activating Token Index: 829

Text #15

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8061. Min Act: 0.0000

Data Index: 709965 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1527665 (The Pile)

Max Activating Token Index: 882

Text #17

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7780. Min Act: -0.0000

Data Index: 865606 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1354188 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1333232 (The Pile)

Max Activating Token Index: 749