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

Dataset: Open Web Text

Neuron 1554 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: 4.1417. Min Range: -4.1417

Max Act: 4.1417. Min Act: -0.1700

Data Index: 1361164 (Open Web Text)

Max Activating Token Index: 152

Text #1

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.9195. Min Act: -0.1700

Data Index: 6110645 (Open Web Text)

Max Activating Token Index: 922

Text #2

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7977. Min Act: -0.1700

Data Index: 4174303 (Open Web Text)

Max Activating Token Index: 519

Text #3

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.9077. Min Act: -0.1700

Data Index: 8565939 (Open Web Text)

Max Activating Token Index: 411

Text #4

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.8757. Min Act: -0.1700

Data Index: 75814 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.8653. Min Act: -0.1700

Data Index: 7943362 (Open Web Text)

Max Activating Token Index: 214

Text #6

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.8701. Min Act: -0.1700

Data Index: 4293862 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.8123. Min Act: -0.1700

Data Index: 5240760 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7819. Min Act: -0.1700

Data Index: 4224270 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7797. Min Act: -0.1700

Data Index: 5601746 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7835. Min Act: -0.1700

Data Index: 2913038 (Open Web Text)

Max Activating Token Index: 163

Text #11

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7959. Min Act: -0.1700

Data Index: 6526172 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7975. Min Act: -0.1700

Data Index: 7893101 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7492. Min Act: -0.1700

Data Index: 1584320 (Open Web Text)

Max Activating Token Index: 257

Text #14

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7163. Min Act: -0.1700

Data Index: 5640655 (Open Web Text)

Max Activating Token Index: 177

Text #15

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7305. Min Act: -0.1700

Data Index: 5901894 (Open Web Text)

Max Activating Token Index: 118

Text #16

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.6827. Min Act: -0.1700

Data Index: 5403726 (Open Web Text)

Max Activating Token Index: 850

Text #17

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.6870. Min Act: -0.1700

Data Index: 2085406 (Open Web Text)

Max Activating Token Index: 298

Text #18

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.6626. Min Act: -0.1700

Data Index: 289666 (Open Web Text)

Max Activating Token Index: 51

Text #19

Max Range: 4.1417. Min Range: -4.1417

Max Act: 3.7029. Min Act: -0.1700

Data Index: 6244995 (Open Web Text)

Max Activating Token Index: 560