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

Dataset: Open Web Text

Neuron 566 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: 2.7429. Min Range: -2.7429

Max Act: 2.7205. Min Act: -0.1551

Data Index: 8201168 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.7429. Min Act: -0.1700

Data Index: 7604321 (Open Web Text)

Max Activating Token Index: 386

Text #2

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.7203. Min Act: -0.1700

Data Index: 4779289 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.7083. Min Act: -0.1700

Data Index: 6957114 (Open Web Text)

Max Activating Token Index: 322

Text #4

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.7176. Min Act: -0.1700

Data Index: 6957115 (Open Web Text)

Max Activating Token Index: 833

Text #5

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.7080. Min Act: -0.1654

Data Index: 8201169 (Open Web Text)

Max Activating Token Index: 586

Text #6

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.7124. Min Act: -0.1700

Data Index: 7179171 (Open Web Text)

Max Activating Token Index: 219

Text #7

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6688. Min Act: -0.1700

Data Index: 217150 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6520. Min Act: -0.1700

Data Index: 4779280 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6630. Min Act: -0.1700

Data Index: 4779288 (Open Web Text)

Max Activating Token Index: 668

Text #10

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6703. Min Act: -0.1700

Data Index: 4779297 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6467. Min Act: -0.1700

Data Index: 4615441 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6654. Min Act: -0.1693

Data Index: 3935675 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6392. Min Act: -0.1700

Data Index: 2118754 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6466. Min Act: -0.1700

Data Index: 4922908 (Open Web Text)

Max Activating Token Index: 315

Text #15

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6210. Min Act: -0.1700

Data Index: 5486777 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6015. Min Act: -0.1700

Data Index: 6643832 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.5816. Min Act: -0.1678

Data Index: 8201173 (Open Web Text)

Max Activating Token Index: 841

Text #18

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.6074. Min Act: -0.1699

Data Index: 6643848 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 2.7429. Min Range: -2.7429

Max Act: 2.5985. Min Act: -0.1700

Data Index: 1753739 (Open Web Text)

Max Activating Token Index: 32