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

Dataset: Open Web Text

Neuron 1657 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: 4.0730. Min Range: -4.0730

Max Act: 4.0730. Min Act: -0.1700

Data Index: 4095540 (Open Web Text)

Max Activating Token Index: 624

Text #1

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8623. Min Act: -0.1700

Data Index: 2252774 (Open Web Text)

Max Activating Token Index: 256

Text #2

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8739. Min Act: -0.1700

Data Index: 6814037 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.9060. Min Act: -0.1700

Data Index: 7288293 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8858. Min Act: -0.1700

Data Index: 4147158 (Open Web Text)

Max Activating Token Index: 391

Text #5

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8560. Min Act: -0.1700

Data Index: 7619874 (Open Web Text)

Max Activating Token Index: 791

Text #6

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8484. Min Act: -0.1700

Data Index: 1025295 (Open Web Text)

Max Activating Token Index: 423

Text #7

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8148. Min Act: -0.1700

Data Index: 8435431 (Open Web Text)

Max Activating Token Index: 800

Text #8

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.8214. Min Act: -0.1700

Data Index: 5107159 (Open Web Text)

Max Activating Token Index: 554

Text #9

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7945. Min Act: -0.1700

Data Index: 799407 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7752. Min Act: -0.1700

Data Index: 2149275 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7432. Min Act: -0.1700

Data Index: 271384 (Open Web Text)

Max Activating Token Index: 117

Text #12

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7506. Min Act: -0.1700

Data Index: 6857062 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7614. Min Act: -0.1700

Data Index: 2257796 (Open Web Text)

Max Activating Token Index: 612

Text #14

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7455. Min Act: -0.1700

Data Index: 8539394 (Open Web Text)

Max Activating Token Index: 573

Text #15

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7670. Min Act: -0.1700

Data Index: 4986886 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.6682. Min Act: -0.1700

Data Index: 6382718 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7163. Min Act: -0.1700

Data Index: 2541030 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.7051. Min Act: -0.1700

Data Index: 1025293 (Open Web Text)

Max Activating Token Index: 693

Text #19

Max Range: 4.0730. Min Range: -4.0730

Max Act: 3.6721. Min Act: -0.1700

Data Index: 4363435 (Open Web Text)

Max Activating Token Index: 230