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

Dataset: Open Web Text

Neuron 221 in Layer 3

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: 4.8775. Min Range: -4.8775

Max Act: 4.8775. Min Act: -0.1700

Data Index: 6927853 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.8246. Min Act: -0.1700

Data Index: 5630209 (Open Web Text)

Max Activating Token Index: 447

Text #2

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7960. Min Act: -0.1700

Data Index: 215704 (Open Web Text)

Max Activating Token Index: 123

Text #3

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7841. Min Act: -0.1700

Data Index: 5312145 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7669. Min Act: -0.1700

Data Index: 5963740 (Open Web Text)

Max Activating Token Index: 1006

Text #5

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7479. Min Act: -0.1700

Data Index: 6187503 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7728. Min Act: -0.1700

Data Index: 5852563 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7248. Min Act: -0.1700

Data Index: 1476170 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7065. Min Act: -0.1700

Data Index: 8165719 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7035. Min Act: -0.1700

Data Index: 6085575 (Open Web Text)

Max Activating Token Index: 308

Text #10

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6937. Min Act: -0.1700

Data Index: 1496095 (Open Web Text)

Max Activating Token Index: 986

Text #11

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6695. Min Act: -0.1700

Data Index: 5394031 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6567. Min Act: -0.1700

Data Index: 3275031 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6639. Min Act: -0.1700

Data Index: 6688955 (Open Web Text)

Max Activating Token Index: 621

Text #14

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6419. Min Act: -0.1700

Data Index: 627154 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6714. Min Act: -0.1700

Data Index: 3909685 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6207. Min Act: -0.1700

Data Index: 4970286 (Open Web Text)

Max Activating Token Index: 195

Text #17

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6747. Min Act: -0.1700

Data Index: 4981712 (Open Web Text)

Max Activating Token Index: 216

Text #18

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6519. Min Act: -0.1700

Data Index: 3988414 (Open Web Text)

Max Activating Token Index: 109

Text #19

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6198. Min Act: -0.1700

Data Index: 3040909 (Open Web Text)

Max Activating Token Index: 320