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

Dataset: Open Web Text

Neuron 220 in Layer 2

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: 5.3260. Min Range: -5.3260

Max Act: 5.3208. Min Act: -0.1700

Data Index: 8323126 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.3260. Min Act: -0.1700

Data Index: 5032481 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.3024. Min Act: -0.1700

Data Index: 6882558 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.2615. Min Act: -0.1700

Data Index: 2174167 (Open Web Text)

Max Activating Token Index: 249

Text #4

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.2649. Min Act: -0.1700

Data Index: 6087640 (Open Web Text)

Max Activating Token Index: 813

Text #5

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.2507. Min Act: -0.1700

Data Index: 3957288 (Open Web Text)

Max Activating Token Index: 808

Text #6

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.1350. Min Act: -0.1700

Data Index: 3814707 (Open Web Text)

Max Activating Token Index: 425

Text #7

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.1624. Min Act: -0.1700

Data Index: 4037244 (Open Web Text)

Max Activating Token Index: 221

Text #8

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.1549. Min Act: -0.1700

Data Index: 189656 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.1375. Min Act: -0.1700

Data Index: 7528644 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.1127. Min Act: -0.1700

Data Index: 4975756 (Open Web Text)

Max Activating Token Index: 949

Text #11

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.0585. Min Act: -0.1700

Data Index: 4429007 (Open Web Text)

Max Activating Token Index: 59

Text #12

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.0525. Min Act: -0.1700

Data Index: 3820001 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.0403. Min Act: -0.1700

Data Index: 7546377 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.3260. Min Range: -5.3260

Max Act: 5.0150. Min Act: -0.1700

Data Index: 8730210 (Open Web Text)

Max Activating Token Index: 479

Text #15

Max Range: 5.3260. Min Range: -5.3260

Max Act: 4.9758. Min Act: -0.1700

Data Index: 6656095 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 5.3260. Min Range: -5.3260

Max Act: 4.9512. Min Act: -0.1700

Data Index: 5523965 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 5.3260. Min Range: -5.3260

Max Act: 4.9193. Min Act: -0.1700

Data Index: 473951 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 5.3260. Min Range: -5.3260

Max Act: 4.9641. Min Act: -0.1700

Data Index: 5504794 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 5.3260. Min Range: -5.3260

Max Act: 4.9102. Min Act: -0.1700

Data Index: 95710 (Open Web Text)

Max Activating Token Index: 81