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

Dataset: Open Web Text

Neuron 670 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: 3.2410. Min Range: -3.2410

Max Act: 3.2410. Min Act: -0.1700

Data Index: 1427379 (Open Web Text)

Max Activating Token Index: 255

Text #1

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.2059. Min Act: -0.1700

Data Index: 8802445 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1792. Min Act: -0.1700

Data Index: 7150016 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1481. Min Act: -0.1700

Data Index: 7269801 (Open Web Text)

Max Activating Token Index: 296

Text #4

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1431. Min Act: -0.1700

Data Index: 6319985 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1198. Min Act: -0.1700

Data Index: 5817679 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1377. Min Act: -0.1700

Data Index: 2766812 (Open Web Text)

Max Activating Token Index: 1009

Text #7

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1373. Min Act: -0.1700

Data Index: 6443299 (Open Web Text)

Max Activating Token Index: 81

Text #8

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1074. Min Act: -0.1700

Data Index: 1896075 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0809. Min Act: -0.1700

Data Index: 3248599 (Open Web Text)

Max Activating Token Index: 730

Text #10

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0931. Min Act: -0.1700

Data Index: 1673290 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.1095. Min Act: -0.1700

Data Index: 8098224 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0853. Min Act: -0.1700

Data Index: 4081892 (Open Web Text)

Max Activating Token Index: 975

Text #13

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0743. Min Act: -0.1700

Data Index: 4504045 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0623. Min Act: -0.1700

Data Index: 5355133 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0811. Min Act: -0.1700

Data Index: 2916106 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0591. Min Act: -0.1700

Data Index: 6968509 (Open Web Text)

Max Activating Token Index: 327

Text #17

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0644. Min Act: -0.1700

Data Index: 4124357 (Open Web Text)

Max Activating Token Index: 554

Text #18

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0402. Min Act: -0.1700

Data Index: 114655 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 3.2410. Min Range: -3.2410

Max Act: 3.0364. Min Act: -0.1700

Data Index: 2252246 (Open Web Text)

Max Activating Token Index: 63