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

Dataset: Open Web Text

Neuron 2786 in Layer 6

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: 5.9314. Min Range: -5.9314

Max Act: 5.9314. Min Act: -0.1700

Data Index: 3554138 (Open Web Text)

Max Activating Token Index: 701

Text #1

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.8509. Min Act: -0.1700

Data Index: 4901930 (Open Web Text)

Max Activating Token Index: 259

Text #2

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.8082. Min Act: -0.1700

Data Index: 8616870 (Open Web Text)

Max Activating Token Index: 695

Text #3

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7776. Min Act: -0.1700

Data Index: 3312203 (Open Web Text)

Max Activating Token Index: 753

Text #4

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7911. Min Act: -0.1700

Data Index: 5875796 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7990. Min Act: -0.1700

Data Index: 2142467 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7308. Min Act: -0.1700

Data Index: 6270473 (Open Web Text)

Max Activating Token Index: 388

Text #7

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7566. Min Act: -0.1700

Data Index: 8655279 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7734. Min Act: -0.1700

Data Index: 3141637 (Open Web Text)

Max Activating Token Index: 341

Text #9

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7156. Min Act: -0.1700

Data Index: 7165051 (Open Web Text)

Max Activating Token Index: 540

Text #10

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.7577. Min Act: -0.1700

Data Index: 8576696 (Open Web Text)

Max Activating Token Index: 298

Text #11

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6789. Min Act: -0.1700

Data Index: 3589466 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6987. Min Act: -0.1700

Data Index: 2202979 (Open Web Text)

Max Activating Token Index: 308

Text #13

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6667. Min Act: -0.1700

Data Index: 355517 (Open Web Text)

Max Activating Token Index: 236

Text #14

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6569. Min Act: -0.1700

Data Index: 7156829 (Open Web Text)

Max Activating Token Index: 407

Text #15

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6893. Min Act: -0.1700

Data Index: 16169 (Open Web Text)

Max Activating Token Index: 816

Text #16

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6639. Min Act: -0.1700

Data Index: 6153556 (Open Web Text)

Max Activating Token Index: 197

Text #17

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6424. Min Act: -0.1700

Data Index: 2504838 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6606. Min Act: -0.1700

Data Index: 2534193 (Open Web Text)

Max Activating Token Index: 978

Text #19

Max Range: 5.9314. Min Range: -5.9314

Max Act: 5.6676. Min Act: -0.1700

Data Index: 8664759 (Open Web Text)

Max Activating Token Index: 359