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

Dataset: Open Web Text

Neuron 2769 in Layer 0

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: 1.6156. Min Range: -1.6156

Max Act: 1.6156. Min Act: -0.1163

Data Index: 630966 (Open Web Text)

Max Activating Token Index: 806

Text #1

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5885. Min Act: -0.0965

Data Index: 7494457 (Open Web Text)

Max Activating Token Index: 327

Text #2

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5870. Min Act: -0.1468

Data Index: 8549122 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5805. Min Act: -0.0806

Data Index: 7526741 (Open Web Text)

Max Activating Token Index: 525

Text #4

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5821. Min Act: -0.1337

Data Index: 4211203 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5713. Min Act: -0.1133

Data Index: 6174723 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5642. Min Act: -0.1480

Data Index: 418219 (Open Web Text)

Max Activating Token Index: 630

Text #7

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5677. Min Act: -0.1315

Data Index: 5188938 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5721. Min Act: -0.1028

Data Index: 354852 (Open Web Text)

Max Activating Token Index: 989

Text #9

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5643. Min Act: -0.1386

Data Index: 7297817 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5557. Min Act: -0.1026

Data Index: 6393335 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5608. Min Act: -0.0973

Data Index: 4663113 (Open Web Text)

Max Activating Token Index: 718

Text #12

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5568. Min Act: -0.1503

Data Index: 1615360 (Open Web Text)

Max Activating Token Index: 656

Text #13

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5610. Min Act: -0.1501

Data Index: 4869015 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5636. Min Act: -0.1442

Data Index: 8731709 (Open Web Text)

Max Activating Token Index: 360

Text #15

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5615. Min Act: -0.1555

Data Index: 3682346 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5543. Min Act: -0.1115

Data Index: 7269048 (Open Web Text)

Max Activating Token Index: 561

Text #17

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5612. Min Act: -0.1473

Data Index: 6472048 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5472. Min Act: -0.1323

Data Index: 5337144 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 1.6156. Min Range: -1.6156

Max Act: 1.5480. Min Act: -0.1344

Data Index: 3067373 (Open Web Text)

Max Activating Token Index: 13