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

Dataset: Open Web Text

Neuron 162 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: 8.8172. Min Range: -8.8172

Max Act: 8.8172. Min Act: -0.1700

Data Index: 655160 (Open Web Text)

Max Activating Token Index: 791

Text #1

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.6747. Min Act: -0.1700

Data Index: 1122290 (Open Web Text)

Max Activating Token Index: 789

Text #2

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.7009. Min Act: -0.1700

Data Index: 15792 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.6613. Min Act: -0.1700

Data Index: 2533794 (Open Web Text)

Max Activating Token Index: 809

Text #4

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.7730. Min Act: -0.1700

Data Index: 5565494 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.5220. Min Act: -0.1700

Data Index: 4486249 (Open Web Text)

Max Activating Token Index: 799

Text #6

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.5121. Min Act: -0.1700

Data Index: 5052198 (Open Web Text)

Max Activating Token Index: 771

Text #7

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.4315. Min Act: -0.1700

Data Index: 2611365 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.4712. Min Act: -0.1700

Data Index: 546829 (Open Web Text)

Max Activating Token Index: 817

Text #9

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.3274. Min Act: -0.1700

Data Index: 7229906 (Open Web Text)

Max Activating Token Index: 803

Text #10

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.4714. Min Act: -0.1700

Data Index: 1917456 (Open Web Text)

Max Activating Token Index: 803

Text #11

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.3583. Min Act: -0.1700

Data Index: 1138344 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.3905. Min Act: -0.1700

Data Index: 7529216 (Open Web Text)

Max Activating Token Index: 807

Text #13

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.3805. Min Act: -0.1700

Data Index: 2141288 (Open Web Text)

Max Activating Token Index: 826

Text #14

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.2412. Min Act: -0.1700

Data Index: 3997393 (Open Web Text)

Max Activating Token Index: 832

Text #15

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.2365. Min Act: -0.1700

Data Index: 432897 (Open Web Text)

Max Activating Token Index: 754

Text #16

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.2723. Min Act: -0.1700

Data Index: 367239 (Open Web Text)

Max Activating Token Index: 762

Text #17

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.2250. Min Act: -0.1700

Data Index: 8517294 (Open Web Text)

Max Activating Token Index: 777

Text #18

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.2666. Min Act: -0.1700

Data Index: 7388346 (Open Web Text)

Max Activating Token Index: 837

Text #19

Max Range: 8.8172. Min Range: -8.8172

Max Act: 8.1493. Min Act: -0.1700

Data Index: 7475570 (Open Web Text)

Max Activating Token Index: 765