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

Dataset: Open Web Text

Neuron 653 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: 5.0576. Min Range: -5.0576

Max Act: 5.0576. Min Act: -0.1700

Data Index: 4721228 (Open Web Text)

Max Activating Token Index: 762

Text #1

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9604. Min Act: -0.1700

Data Index: 5198247 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9311. Min Act: -0.1700

Data Index: 5898214 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9170. Min Act: -0.1700

Data Index: 6930490 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8978. Min Act: -0.1700

Data Index: 3872787 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8807. Min Act: -0.1700

Data Index: 6230593 (Open Web Text)

Max Activating Token Index: 863

Text #6

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8650. Min Act: -0.1700

Data Index: 775798 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8764. Min Act: -0.1700

Data Index: 2074310 (Open Web Text)

Max Activating Token Index: 82

Text #8

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8848. Min Act: -0.1700

Data Index: 1226512 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8984. Min Act: -0.1700

Data Index: 4330118 (Open Web Text)

Max Activating Token Index: 453

Text #10

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8482. Min Act: -0.1700

Data Index: 8314098 (Open Web Text)

Max Activating Token Index: 837

Text #11

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8804. Min Act: -0.1700

Data Index: 7911942 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8267. Min Act: -0.1700

Data Index: 7130730 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8324. Min Act: -0.1700

Data Index: 6816478 (Open Web Text)

Max Activating Token Index: 903

Text #14

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8478. Min Act: -0.1700

Data Index: 8607793 (Open Web Text)

Max Activating Token Index: 433

Text #15

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8231. Min Act: -0.1700

Data Index: 8417216 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8172. Min Act: -0.1700

Data Index: 3371638 (Open Web Text)

Max Activating Token Index: 822

Text #17

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8199. Min Act: -0.1700

Data Index: 181342 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8461. Min Act: -0.1700

Data Index: 4776092 (Open Web Text)

Max Activating Token Index: 643

Text #19

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8019. Min Act: -0.1700

Data Index: 7101650 (Open Web Text)

Max Activating Token Index: 10