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

Dataset: Open Web Text

Neuron 1778 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: 1.7418. Min Range: -1.7418

Max Act: 1.7418. Min Act: -0.1700

Data Index: 4855308 (Open Web Text)

Max Activating Token Index: 623

Text #1

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.7364. Min Act: -0.1700

Data Index: 7144439 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.7228. Min Act: -0.1700

Data Index: 4859399 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.7269. Min Act: -0.1700

Data Index: 3417217 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.7218. Min Act: -0.1700

Data Index: 188413 (Open Web Text)

Max Activating Token Index: 286

Text #5

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6860. Min Act: -0.1700

Data Index: 2601309 (Open Web Text)

Max Activating Token Index: 78

Text #6

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6875. Min Act: -0.1700

Data Index: 7673826 (Open Web Text)

Max Activating Token Index: 351

Text #7

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6840. Min Act: -0.1700

Data Index: 4028814 (Open Web Text)

Max Activating Token Index: 247

Text #8

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6788. Min Act: -0.1690

Data Index: 1218860 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6683. Min Act: -0.1700

Data Index: 857789 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6658. Min Act: -0.1700

Data Index: 5291538 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6489. Min Act: -0.1700

Data Index: 3282657 (Open Web Text)

Max Activating Token Index: 856

Text #12

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6780. Min Act: -0.1700

Data Index: 6083241 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6519. Min Act: -0.1700

Data Index: 372627 (Open Web Text)

Max Activating Token Index: 234

Text #14

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6587. Min Act: -0.1700

Data Index: 2898882 (Open Web Text)

Max Activating Token Index: 716

Text #15

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6703. Min Act: -0.1700

Data Index: 897829 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6696. Min Act: -0.1700

Data Index: 6868170 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6427. Min Act: -0.1700

Data Index: 6423166 (Open Web Text)

Max Activating Token Index: 670

Text #18

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6485. Min Act: -0.1696

Data Index: 2097529 (Open Web Text)

Max Activating Token Index: 836

Text #19

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6407. Min Act: -0.1700

Data Index: 2483419 (Open Web Text)

Max Activating Token Index: 241