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

Dataset: Open Web Text

Neuron 2574 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: 3.7238. Min Range: -3.7238

Max Act: 3.7238. Min Act: -0.1700

Data Index: 2889629 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6859. Min Act: -0.1700

Data Index: 1698115 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6006. Min Act: -0.1700

Data Index: 5536777 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5335. Min Act: -0.1700

Data Index: 5914618 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5568. Min Act: -0.1700

Data Index: 1318794 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5635. Min Act: -0.1700

Data Index: 8569421 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5488. Min Act: -0.1700

Data Index: 8618418 (Open Web Text)

Max Activating Token Index: 923

Text #7

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5041. Min Act: -0.1700

Data Index: 31720 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5085. Min Act: -0.1700

Data Index: 2879227 (Open Web Text)

Max Activating Token Index: 452

Text #9

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5645. Min Act: -0.1700

Data Index: 2541115 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5013. Min Act: -0.1700

Data Index: 7381586 (Open Web Text)

Max Activating Token Index: 985

Text #11

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5427. Min Act: -0.1700

Data Index: 1548527 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.4746. Min Act: -0.1700

Data Index: 5439578 (Open Web Text)

Max Activating Token Index: 512

Text #13

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5068. Min Act: -0.1700

Data Index: 6402867 (Open Web Text)

Max Activating Token Index: 150

Text #14

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.4798. Min Act: -0.1700

Data Index: 3239145 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.4952. Min Act: -0.1700

Data Index: 1029551 (Open Web Text)

Max Activating Token Index: 892

Text #16

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.4566. Min Act: -0.1700

Data Index: 4186747 (Open Web Text)

Max Activating Token Index: 149

Text #17

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.4932. Min Act: -0.1700

Data Index: 970070 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5159. Min Act: -0.1700

Data Index: 5711066 (Open Web Text)

Max Activating Token Index: 467

Text #19

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.4674. Min Act: -0.1700

Data Index: 4700331 (Open Web Text)

Max Activating Token Index: 150