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

Dataset: Open Web Text

Neuron 1872 in Layer 6

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: 4.9391. Min Range: -4.9391

Max Act: 4.9391. Min Act: -0.1700

Data Index: 2567717 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.8747. Min Act: -0.1700

Data Index: 1239375 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.8466. Min Act: -0.1700

Data Index: 8653121 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.8305. Min Act: -0.1700

Data Index: 4344321 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.8132. Min Act: -0.1700

Data Index: 604642 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7880. Min Act: -0.1700

Data Index: 1006711 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7744. Min Act: -0.1700

Data Index: 6272900 (Open Web Text)

Max Activating Token Index: 180

Text #7

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7681. Min Act: -0.1700

Data Index: 1181152 (Open Web Text)

Max Activating Token Index: 537

Text #8

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7716. Min Act: -0.1700

Data Index: 7686721 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7797. Min Act: -0.1700

Data Index: 6127912 (Open Web Text)

Max Activating Token Index: 220

Text #10

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7849. Min Act: -0.1700

Data Index: 4957802 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.6854. Min Act: -0.1700

Data Index: 2887582 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7030. Min Act: -0.1700

Data Index: 7614420 (Open Web Text)

Max Activating Token Index: 159

Text #13

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.7108. Min Act: -0.1700

Data Index: 842543 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.6625. Min Act: -0.1700

Data Index: 6182241 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.6753. Min Act: -0.1700

Data Index: 809515 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.6813. Min Act: -0.1700

Data Index: 380117 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.6806. Min Act: -0.1700

Data Index: 2621622 (Open Web Text)

Max Activating Token Index: 97

Text #18

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.6331. Min Act: -0.1700

Data Index: 3998013 (Open Web Text)

Max Activating Token Index: 721

Text #19

Max Range: 4.9391. Min Range: -4.9391

Max Act: 4.6274. Min Act: -0.1700

Data Index: 862141 (Open Web Text)

Max Activating Token Index: 812