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

Dataset: Open Web Text

Neuron 2037 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: 4.2382. Min Range: -4.2382

Max Act: 4.2382. Min Act: -0.1700

Data Index: 5743170 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.1358. Min Act: -0.1700

Data Index: 5857932 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.1195. Min Act: -0.1700

Data Index: 1869379 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.1299. Min Act: -0.1700

Data Index: 8200560 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.1071. Min Act: -0.1700

Data Index: 6096524 (Open Web Text)

Max Activating Token Index: 22

Text #5

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.1112. Min Act: -0.1700

Data Index: 5247604 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0979. Min Act: -0.1700

Data Index: 3552846 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0853. Min Act: -0.1700

Data Index: 1029740 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0642. Min Act: -0.1700

Data Index: 7576220 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0662. Min Act: -0.1700

Data Index: 3141620 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0749. Min Act: -0.1700

Data Index: 5094510 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0728. Min Act: -0.1700

Data Index: 1011271 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0582. Min Act: -0.1700

Data Index: 4342299 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0805. Min Act: -0.1700

Data Index: 563401 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0754. Min Act: -0.1700

Data Index: 8583238 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0302. Min Act: -0.1700

Data Index: 4820027 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0474. Min Act: -0.1700

Data Index: 8511411 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0542. Min Act: -0.1700

Data Index: 2383414 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0292. Min Act: -0.1700

Data Index: 5677595 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 4.2382. Min Range: -4.2382

Max Act: 4.0336. Min Act: -0.1700

Data Index: 990418 (Open Web Text)

Max Activating Token Index: 16