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

Dataset: Open Web Text

Neuron 2752 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: 4.2731. Min Range: -4.2731

Max Act: 4.2731. Min Act: -0.1700

Data Index: 8291476 (Open Web Text)

Max Activating Token Index: 813

Text #1

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.2300. Min Act: -0.1700

Data Index: 7963443 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.2222. Min Act: -0.1700

Data Index: 6727706 (Open Web Text)

Max Activating Token Index: 139

Text #3

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.2253. Min Act: -0.1700

Data Index: 1344383 (Open Web Text)

Max Activating Token Index: 287

Text #4

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.2579. Min Act: -0.1700

Data Index: 6850780 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.2125. Min Act: -0.1700

Data Index: 6215751 (Open Web Text)

Max Activating Token Index: 1003

Text #6

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1964. Min Act: -0.1700

Data Index: 4633380 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.2092. Min Act: -0.1700

Data Index: 7423822 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1897. Min Act: -0.1700

Data Index: 4781189 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1895. Min Act: -0.1700

Data Index: 643911 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1692. Min Act: -0.1700

Data Index: 5388813 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1951. Min Act: -0.1700

Data Index: 8396065 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1798. Min Act: -0.1700

Data Index: 926247 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1909. Min Act: -0.1700

Data Index: 366916 (Open Web Text)

Max Activating Token Index: 146

Text #14

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1688. Min Act: -0.1700

Data Index: 3380363 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1612. Min Act: -0.1700

Data Index: 526285 (Open Web Text)

Max Activating Token Index: 370

Text #16

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1860. Min Act: -0.1700

Data Index: 6636267 (Open Web Text)

Max Activating Token Index: 672

Text #17

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1705. Min Act: -0.1700

Data Index: 5919933 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1781. Min Act: -0.1700

Data Index: 5816842 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 4.2731. Min Range: -4.2731

Max Act: 4.1199. Min Act: -0.1700

Data Index: 5668424 (Open Web Text)

Max Activating Token Index: 691