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

Dataset: Open Web Text

Neuron 1918 in Layer 1

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: 1.8716. Min Range: -1.8716

Max Act: 1.8716. Min Act: -0.1700

Data Index: 8741836 (Open Web Text)

Max Activating Token Index: 806

Text #1

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.8105. Min Act: -0.1700

Data Index: 3179304 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7989. Min Act: -0.1700

Data Index: 5078027 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7936. Min Act: -0.1700

Data Index: 5904529 (Open Web Text)

Max Activating Token Index: 207

Text #4

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7899. Min Act: -0.1700

Data Index: 4444115 (Open Web Text)

Max Activating Token Index: 838

Text #5

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7687. Min Act: -0.1700

Data Index: 3315703 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7704. Min Act: -0.1700

Data Index: 885851 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7579. Min Act: -0.1700

Data Index: 881644 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7643. Min Act: -0.1700

Data Index: 7486436 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7535. Min Act: -0.1700

Data Index: 1495194 (Open Web Text)

Max Activating Token Index: 467

Text #10

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7477. Min Act: -0.1700

Data Index: 8628641 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7489. Min Act: -0.1700

Data Index: 7342051 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7468. Min Act: -0.1700

Data Index: 5862733 (Open Web Text)

Max Activating Token Index: 76

Text #13

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7547. Min Act: -0.1700

Data Index: 2250744 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7549. Min Act: -0.1700

Data Index: 2533077 (Open Web Text)

Max Activating Token Index: 247

Text #15

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7455. Min Act: -0.1700

Data Index: 7797665 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7576. Min Act: -0.1700

Data Index: 7703973 (Open Web Text)

Max Activating Token Index: 657

Text #17

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7593. Min Act: -0.1700

Data Index: 7525013 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7478. Min Act: -0.1700

Data Index: 1191987 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7469. Min Act: -0.1700

Data Index: 5950967 (Open Web Text)

Max Activating Token Index: 664