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

Dataset: Open Web Text

Neuron 563 in Layer 3

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: 7.4306. Min Range: -7.4306

Max Act: 7.4306. Min Act: -0.1700

Data Index: 6055250 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.3258. Min Act: -0.1700

Data Index: 8255045 (Open Web Text)

Max Activating Token Index: 472

Text #2

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.4039. Min Act: -0.1700

Data Index: 2319669 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1288. Min Act: -0.1700

Data Index: 3391132 (Open Web Text)

Max Activating Token Index: 744

Text #4

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.0828. Min Act: -0.1700

Data Index: 5643571 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1582. Min Act: -0.1700

Data Index: 4720988 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1167. Min Act: -0.1700

Data Index: 2079534 (Open Web Text)

Max Activating Token Index: 792

Text #7

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.0085. Min Act: -0.1700

Data Index: 2369029 (Open Web Text)

Max Activating Token Index: 633

Text #8

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1409. Min Act: -0.1700

Data Index: 2108029 (Open Web Text)

Max Activating Token Index: 474

Text #9

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1866. Min Act: -0.1700

Data Index: 346801 (Open Web Text)

Max Activating Token Index: 424

Text #10

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1484. Min Act: -0.1700

Data Index: 7011279 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.3276. Min Act: -0.1700

Data Index: 4491883 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1109. Min Act: -0.1700

Data Index: 4654615 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.0759. Min Act: -0.1700

Data Index: 8584210 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.0714. Min Act: -0.1700

Data Index: 5650335 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1673. Min Act: -0.1700

Data Index: 4134570 (Open Web Text)

Max Activating Token Index: 239

Text #16

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1007. Min Act: -0.1700

Data Index: 1609320 (Open Web Text)

Max Activating Token Index: 271

Text #17

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.0392. Min Act: -0.1700

Data Index: 6933337 (Open Web Text)

Max Activating Token Index: 432

Text #18

Max Range: 7.4306. Min Range: -7.4306

Max Act: 6.9154. Min Act: -0.1700

Data Index: 1878578 (Open Web Text)

Max Activating Token Index: 894

Text #19

Max Range: 7.4306. Min Range: -7.4306

Max Act: 7.1547. Min Act: -0.1700

Data Index: 4741789 (Open Web Text)

Max Activating Token Index: 445