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

Dataset: Open Web Text

Neuron 612 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: 3.6053. Min Range: -3.6053

Max Act: 3.6053. Min Act: -0.1700

Data Index: 104208 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.5809. Min Act: -0.1700

Data Index: 6377156 (Open Web Text)

Max Activating Token Index: 351

Text #2

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.5135. Min Act: -0.1700

Data Index: 1868707 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.5189. Min Act: -0.1700

Data Index: 437363 (Open Web Text)

Max Activating Token Index: 534

Text #4

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.5034. Min Act: -0.1700

Data Index: 4190402 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.5071. Min Act: -0.1700

Data Index: 3264796 (Open Web Text)

Max Activating Token Index: 816

Text #6

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1486507 (Open Web Text)

Max Activating Token Index: 231

Text #7

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4577. Min Act: -0.1700

Data Index: 5225480 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4605. Min Act: -0.1700

Data Index: 3070087 (Open Web Text)

Max Activating Token Index: 179

Text #9

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4536. Min Act: -0.1700

Data Index: 1878738 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4354. Min Act: -0.1700

Data Index: 5570088 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4379. Min Act: -0.1700

Data Index: 6935565 (Open Web Text)

Max Activating Token Index: 775

Text #12

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4321. Min Act: -0.1700

Data Index: 3797439 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.4194. Min Act: -0.1700

Data Index: 2626201 (Open Web Text)

Max Activating Token Index: 448

Text #14

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.3854. Min Act: -0.1700

Data Index: 3817113 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.3682. Min Act: -0.1700

Data Index: 6342649 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.3889. Min Act: -0.1700

Data Index: 7983490 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.3651. Min Act: -0.1700

Data Index: 8236258 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.3891. Min Act: -0.1700

Data Index: 1399576 (Open Web Text)

Max Activating Token Index: 474

Text #19

Max Range: 3.6053. Min Range: -3.6053

Max Act: 3.3617. Min Act: -0.1700

Data Index: 5882877 (Open Web Text)

Max Activating Token Index: 497