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

Dataset: Open Web Text

Neuron 449 in Layer 5

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: 3.2730. Min Range: -3.2730

Max Act: 3.2730. Min Act: -0.1700

Data Index: 6215261 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.2369. Min Act: -0.1700

Data Index: 6800412 (Open Web Text)

Max Activating Token Index: 565

Text #2

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.2504. Min Act: -0.1700

Data Index: 2393556 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.2177. Min Act: -0.1700

Data Index: 7730073 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.2098. Min Act: -0.1700

Data Index: 5820367 (Open Web Text)

Max Activating Token Index: 201

Text #5

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1817. Min Act: -0.1700

Data Index: 3012380 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1563. Min Act: -0.1700

Data Index: 6777626 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1623. Min Act: -0.1700

Data Index: 5771989 (Open Web Text)

Max Activating Token Index: 747

Text #8

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1588. Min Act: -0.1700

Data Index: 3944394 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1604. Min Act: -0.1700

Data Index: 3529425 (Open Web Text)

Max Activating Token Index: 918

Text #10

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1703. Min Act: -0.1700

Data Index: 73712 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1613. Min Act: -0.1700

Data Index: 801284 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1599. Min Act: -0.1700

Data Index: 6012572 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1408. Min Act: -0.1700

Data Index: 3052777 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1447. Min Act: -0.1700

Data Index: 5801381 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1227. Min Act: -0.1700

Data Index: 8570128 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1220. Min Act: -0.1700

Data Index: 4419022 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.0950. Min Act: -0.1700

Data Index: 4996954 (Open Web Text)

Max Activating Token Index: 640

Text #18

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.1229. Min Act: -0.1700

Data Index: 1999389 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 3.2730. Min Range: -3.2730

Max Act: 3.0801. Min Act: -0.1700

Data Index: 3115700 (Open Web Text)

Max Activating Token Index: 711