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

Dataset: The Pile

Neuron 2564 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: 0.9672. Min Range: -0.9672

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1064380 (The Pile)

Max Activating Token Index: 481

Text #1

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1242599 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1738838 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.9227. Min Act: -0.0000

Data Index: 186056 (The Pile)

Max Activating Token Index: 641

Text #4

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8614. Min Act: -0.0000

Data Index: 125397 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1837834 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1699693 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8104. Min Act: -0.0000

Data Index: 330331 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8011. Min Act: -0.0000

Data Index: 337644 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1521532 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1659575 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1251066 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8182. Min Act: -0.0000

Data Index: 70590 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8092. Min Act: -0.0000

Data Index: 976549 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1721227 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1055659 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8764. Min Act: 0.0000

Data Index: 718843 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7558. Min Act: -0.0000

Data Index: 873954 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1104809 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7894. Min Act: -0.0000

Data Index: 512301 (The Pile)

Max Activating Token Index: 595