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

Dataset: Open Web Text

Neuron 2542 in Layer 2

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: 5.1834. Min Range: -5.1834

Max Act: 5.1834. Min Act: -0.1700

Data Index: 6523940 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6816. Min Act: -0.1700

Data Index: 6751046 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6301. Min Act: -0.1700

Data Index: 7476646 (Open Web Text)

Max Activating Token Index: 780

Text #3

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6807. Min Act: -0.1700

Data Index: 1612836 (Open Web Text)

Max Activating Token Index: 238

Text #4

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6653. Min Act: -0.1700

Data Index: 8233097 (Open Web Text)

Max Activating Token Index: 524

Text #5

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6135. Min Act: -0.1700

Data Index: 5412897 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6315. Min Act: -0.1700

Data Index: 5740364 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6014. Min Act: -0.1697

Data Index: 1373954 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6109. Min Act: -0.1700

Data Index: 6125161 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6652. Min Act: -0.1700

Data Index: 8764257 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5683. Min Act: -0.1700

Data Index: 6232050 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5185. Min Act: -0.1700

Data Index: 7793428 (Open Web Text)

Max Activating Token Index: 642

Text #12

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.6054. Min Act: -0.1700

Data Index: 8733758 (Open Web Text)

Max Activating Token Index: 298

Text #13

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5568. Min Act: -0.1700

Data Index: 3948109 (Open Web Text)

Max Activating Token Index: 385

Text #14

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5432. Min Act: -0.1700

Data Index: 973942 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5494. Min Act: -0.1700

Data Index: 6002425 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5553. Min Act: -0.1700

Data Index: 4406860 (Open Web Text)

Max Activating Token Index: 219

Text #17

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.4982. Min Act: -0.1700

Data Index: 1415335 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5702. Min Act: -0.1700

Data Index: 193589 (Open Web Text)

Max Activating Token Index: 389

Text #19

Max Range: 5.1834. Min Range: -5.1834

Max Act: 4.5419. Min Act: -0.1700

Data Index: 769905 (Open Web Text)

Max Activating Token Index: 910