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

Dataset: Open Web Text

Neuron 2602 in Layer 5

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: 4.8626. Min Range: -4.8626

Max Act: 4.8396. Min Act: -0.1700

Data Index: 6689460 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.8556. Min Act: -0.1700

Data Index: 683991 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.8626. Min Act: -0.1700

Data Index: 6856186 (Open Web Text)

Max Activating Token Index: 235

Text #3

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.8521. Min Act: -0.1700

Data Index: 4812120 (Open Web Text)

Max Activating Token Index: 831

Text #4

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.7973. Min Act: -0.1700

Data Index: 3469210 (Open Web Text)

Max Activating Token Index: 823

Text #5

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.8492. Min Act: -0.1700

Data Index: 7473224 (Open Web Text)

Max Activating Token Index: 703

Text #6

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.7748. Min Act: -0.1700

Data Index: 1188658 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.7838. Min Act: -0.1700

Data Index: 4426209 (Open Web Text)

Max Activating Token Index: 826

Text #8

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.7263. Min Act: -0.1700

Data Index: 475925 (Open Web Text)

Max Activating Token Index: 514

Text #9

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.7306. Min Act: -0.1700

Data Index: 222914 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.7331. Min Act: -0.1700

Data Index: 4116907 (Open Web Text)

Max Activating Token Index: 766

Text #11

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.7000. Min Act: -0.1700

Data Index: 787499 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.6475. Min Act: -0.1700

Data Index: 656919 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.6523. Min Act: -0.1700

Data Index: 747453 (Open Web Text)

Max Activating Token Index: 141

Text #14

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.6374. Min Act: -0.1700

Data Index: 609124 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.6879. Min Act: -0.1700

Data Index: 4691447 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.6719. Min Act: -0.1700

Data Index: 4014947 (Open Web Text)

Max Activating Token Index: 872

Text #17

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.6332. Min Act: -0.1700

Data Index: 307379 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.6193. Min Act: -0.1700

Data Index: 46255 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 4.8626. Min Range: -4.8626

Max Act: 4.5897. Min Act: -0.1700

Data Index: 2490379 (Open Web Text)

Max Activating Token Index: 212