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

Dataset: Open Web Text

Neuron 1067 in Layer 5

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: 4.1146. Min Range: -4.1146

Max Act: 4.1146. Min Act: -0.1700

Data Index: 7664573 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.1106. Min Act: -0.1700

Data Index: 451132 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0889. Min Act: -0.1700

Data Index: 519260 (Open Web Text)

Max Activating Token Index: 970

Text #3

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.1094. Min Act: -0.1700

Data Index: 8029467 (Open Web Text)

Max Activating Token Index: 528

Text #4

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0707. Min Act: -0.1700

Data Index: 2485399 (Open Web Text)

Max Activating Token Index: 674

Text #5

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0752. Min Act: -0.1700

Data Index: 4957165 (Open Web Text)

Max Activating Token Index: 709

Text #6

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0559. Min Act: -0.1700

Data Index: 7910148 (Open Web Text)

Max Activating Token Index: 483

Text #7

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0528. Min Act: -0.1700

Data Index: 4247818 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0433. Min Act: -0.1700

Data Index: 5013949 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0199. Min Act: -0.1700

Data Index: 8790106 (Open Web Text)

Max Activating Token Index: 760

Text #10

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0124. Min Act: -0.1700

Data Index: 5550572 (Open Web Text)

Max Activating Token Index: 805

Text #11

Max Range: 4.1146. Min Range: -4.1146

Max Act: 4.0306. Min Act: -0.1700

Data Index: 5549713 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9736. Min Act: -0.1700

Data Index: 7664570 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9609. Min Act: -0.1700

Data Index: 7860693 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9794. Min Act: -0.1700

Data Index: 7040177 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9689. Min Act: -0.1700

Data Index: 8641440 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9555. Min Act: -0.1700

Data Index: 4368173 (Open Web Text)

Max Activating Token Index: 843

Text #17

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9474. Min Act: -0.1700

Data Index: 6497899 (Open Web Text)

Max Activating Token Index: 844

Text #18

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9502. Min Act: -0.1700

Data Index: 2858861 (Open Web Text)

Max Activating Token Index: 786

Text #19

Max Range: 4.1146. Min Range: -4.1146

Max Act: 3.9358. Min Act: -0.1700

Data Index: 5911415 (Open Web Text)

Max Activating Token Index: 853