Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1546 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.1673. Min Act: -0.1700

Data Index: 4675230 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.0877. Min Act: -0.1700

Data Index: 1212218 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.0558. Min Act: -0.1700

Data Index: 3775819 (Open Web Text)

Max Activating Token Index: 603

Text #3

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.0645. Min Act: -0.1700

Data Index: 3643180 (Open Web Text)

Max Activating Token Index: 399

Text #4

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.0234. Min Act: -0.1700

Data Index: 6967934 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 3.1673. Min Range: -3.1673

Max Act: 3.0080. Min Act: -0.1700

Data Index: 8494386 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9899. Min Act: -0.1700

Data Index: 5223746 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9746. Min Act: -0.1700

Data Index: 8708799 (Open Web Text)

Max Activating Token Index: 107

Text #8

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9953. Min Act: -0.1700

Data Index: 1755761 (Open Web Text)

Max Activating Token Index: 308

Text #9

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9665. Min Act: -0.1700

Data Index: 2941717 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9846. Min Act: -0.1700

Data Index: 5393026 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9978. Min Act: -0.1700

Data Index: 6015096 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9715. Min Act: -0.1700

Data Index: 5612861 (Open Web Text)

Max Activating Token Index: 415

Text #13

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9687. Min Act: -0.1700

Data Index: 3144987 (Open Web Text)

Max Activating Token Index: 274

Text #14

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9618. Min Act: -0.1700

Data Index: 127172 (Open Web Text)

Max Activating Token Index: 653

Text #15

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9681. Min Act: -0.1700

Data Index: 3200177 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9579. Min Act: -0.1700

Data Index: 2977018 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9469. Min Act: -0.1700

Data Index: 8426761 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9477. Min Act: -0.1700

Data Index: 6594167 (Open Web Text)

Max Activating Token Index: 817

Text #19

Max Range: 3.1673. Min Range: -3.1673

Max Act: 2.9620. Min Act: -0.1700

Data Index: 7822662 (Open Web Text)

Max Activating Token Index: 852