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

Dataset: Open Web Text

Neuron 2416 in Layer 4

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: 3.7388. Min Range: -3.7388

Max Act: 3.7388. Min Act: -0.1700

Data Index: 5808913 (Open Web Text)

Max Activating Token Index: 626

Text #1

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6937. Min Act: -0.1700

Data Index: 2095014 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.7043. Min Act: -0.1700

Data Index: 1041587 (Open Web Text)

Max Activating Token Index: 770

Text #3

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6737. Min Act: -0.1700

Data Index: 8224347 (Open Web Text)

Max Activating Token Index: 280

Text #4

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.7015. Min Act: -0.1700

Data Index: 7189683 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6444. Min Act: -0.1700

Data Index: 2357920 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6133. Min Act: -0.1700

Data Index: 697441 (Open Web Text)

Max Activating Token Index: 667

Text #7

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6040. Min Act: -0.1700

Data Index: 5677714 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6185. Min Act: -0.1700

Data Index: 5877558 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6238. Min Act: -0.1700

Data Index: 4295113 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.5960. Min Act: -0.1700

Data Index: 6107993 (Open Web Text)

Max Activating Token Index: 241

Text #11

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.5981. Min Act: -0.1700

Data Index: 5880876 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.5943. Min Act: -0.1700

Data Index: 4879992 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.5705. Min Act: -0.1700

Data Index: 7732860 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.5913. Min Act: -0.1700

Data Index: 2612725 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6392. Min Act: -0.1700

Data Index: 7145226 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.5845. Min Act: -0.1700

Data Index: 4063811 (Open Web Text)

Max Activating Token Index: 375

Text #17

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6101. Min Act: -0.1700

Data Index: 5812686 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.6144. Min Act: -0.1700

Data Index: 2921403 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 3.7388. Min Range: -3.7388

Max Act: 3.5817. Min Act: -0.1700

Data Index: 834292 (Open Web Text)

Max Activating Token Index: 315