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

Dataset: Open Web Text

Neuron 115 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: 3.1874. Min Range: -3.1874

Max Act: 3.1859. Min Act: -0.1700

Data Index: 6203026 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1874. Min Act: -0.1700

Data Index: 4293870 (Open Web Text)

Max Activating Token Index: 758

Text #2

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1728. Min Act: -0.1700

Data Index: 1436670 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1836. Min Act: -0.1700

Data Index: 7044056 (Open Web Text)

Max Activating Token Index: 46

Text #4

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1838. Min Act: -0.1700

Data Index: 8210963 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1374. Min Act: -0.1700

Data Index: 6793917 (Open Web Text)

Max Activating Token Index: 649

Text #6

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1280. Min Act: -0.1700

Data Index: 6765086 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1342. Min Act: -0.1700

Data Index: 5404325 (Open Web Text)

Max Activating Token Index: 896

Text #8

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1330. Min Act: -0.1700

Data Index: 7014405 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1419. Min Act: -0.1700

Data Index: 906328 (Open Web Text)

Max Activating Token Index: 371

Text #10

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1496. Min Act: -0.1700

Data Index: 6793920 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1513. Min Act: -0.1700

Data Index: 6793925 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1428. Min Act: -0.1700

Data Index: 4965276 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1542. Min Act: -0.1700

Data Index: 679799 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1195. Min Act: -0.1700

Data Index: 2462479 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1211. Min Act: -0.1700

Data Index: 6793918 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1142. Min Act: -0.1700

Data Index: 1019504 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1364. Min Act: -0.1700

Data Index: 7988138 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1298. Min Act: -0.1700

Data Index: 6793919 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.1393. Min Act: -0.1700

Data Index: 791502 (Open Web Text)

Max Activating Token Index: 271