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

Dataset: Open Web Text

Neuron 2185 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: 1.6104. Min Range: -1.6104

Max Act: 1.6104. Min Act: -0.1700

Data Index: 5324788 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5844. Min Act: -0.1700

Data Index: 1315591 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5735. Min Act: -0.1700

Data Index: 8456764 (Open Web Text)

Max Activating Token Index: 753

Text #3

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5634. Min Act: -0.1693

Data Index: 3590794 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5724. Min Act: -0.1700

Data Index: 4212685 (Open Web Text)

Max Activating Token Index: 975

Text #5

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5611. Min Act: -0.1700

Data Index: 3489761 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5507. Min Act: -0.1700

Data Index: 3124843 (Open Web Text)

Max Activating Token Index: 786

Text #7

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5564. Min Act: -0.1699

Data Index: 8015412 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5485. Min Act: -0.1700

Data Index: 2160376 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5404. Min Act: -0.1700

Data Index: 5512994 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5434. Min Act: -0.1700

Data Index: 881701 (Open Web Text)

Max Activating Token Index: 623

Text #11

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5475. Min Act: -0.1700

Data Index: 7649158 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5318. Min Act: -0.1700

Data Index: 2256319 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5418. Min Act: -0.1700

Data Index: 2361499 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5247. Min Act: -0.1700

Data Index: 5656500 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5237. Min Act: -0.1700

Data Index: 1404952 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5317. Min Act: -0.1700

Data Index: 421486 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5319. Min Act: -0.1700

Data Index: 1529918 (Open Web Text)

Max Activating Token Index: 193

Text #18

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5304. Min Act: -0.1700

Data Index: 6713463 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 1.6104. Min Range: -1.6104

Max Act: 1.5280. Min Act: -0.1700

Data Index: 6655268 (Open Web Text)

Max Activating Token Index: 430