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

Dataset: Open Web Text

Neuron 204 in Layer 1

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: 1.9281. Min Range: -1.9281

Max Act: 1.9213. Min Act: -0.1688

Data Index: 1839350 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.9281. Min Act: -0.1695

Data Index: 6812863 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.9075. Min Act: -0.1700

Data Index: 5918431 (Open Web Text)

Max Activating Token Index: 178

Text #3

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.9052. Min Act: -0.1688

Data Index: 348760 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8910. Min Act: -0.1699

Data Index: 5457281 (Open Web Text)

Max Activating Token Index: 402

Text #5

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8826. Min Act: -0.1700

Data Index: 2770961 (Open Web Text)

Max Activating Token Index: 565

Text #6

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8659. Min Act: -0.1700

Data Index: 3772627 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8679. Min Act: -0.1700

Data Index: 2117521 (Open Web Text)

Max Activating Token Index: 410

Text #8

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8713. Min Act: -0.1700

Data Index: 6812861 (Open Web Text)

Max Activating Token Index: 831

Text #9

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8697. Min Act: -0.1700

Data Index: 7774742 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8706. Min Act: -0.1700

Data Index: 4478177 (Open Web Text)

Max Activating Token Index: 192

Text #11

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8599. Min Act: -0.1700

Data Index: 5507304 (Open Web Text)

Max Activating Token Index: 412

Text #12

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8685. Min Act: -0.1700

Data Index: 8703964 (Open Web Text)

Max Activating Token Index: 686

Text #13

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8557. Min Act: -0.1698

Data Index: 3935769 (Open Web Text)

Max Activating Token Index: 417

Text #14

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8587. Min Act: -0.1700

Data Index: 5553488 (Open Web Text)

Max Activating Token Index: 85

Text #15

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8550. Min Act: -0.1700

Data Index: 4718403 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8546. Min Act: -0.1677

Data Index: 6420128 (Open Web Text)

Max Activating Token Index: 958

Text #17

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8461. Min Act: -0.1700

Data Index: 7254436 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8421. Min Act: -0.1700

Data Index: 5697342 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.8437. Min Act: -0.1700

Data Index: 4866920 (Open Web Text)

Max Activating Token Index: 618