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

Dataset: Open Web Text

Neuron 2246 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: 4.4860. Min Range: -4.4860

Max Act: 4.4860. Min Act: -0.1700

Data Index: 6760405 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.4363. Min Act: -0.1700

Data Index: 5733811 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2991. Min Act: -0.1700

Data Index: 1204126 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2715. Min Act: -0.1700

Data Index: 6675053 (Open Web Text)

Max Activating Token Index: 315

Text #4

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2630. Min Act: -0.1700

Data Index: 8821176 (Open Web Text)

Max Activating Token Index: 752

Text #5

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2648. Min Act: -0.1700

Data Index: 1204143 (Open Web Text)

Max Activating Token Index: 465

Text #6

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2235. Min Act: -0.1700

Data Index: 696617 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2354. Min Act: -0.1700

Data Index: 4121182 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2316. Min Act: -0.1700

Data Index: 779523 (Open Web Text)

Max Activating Token Index: 94

Text #9

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2220. Min Act: -0.1700

Data Index: 1986952 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2014. Min Act: -0.1700

Data Index: 1973986 (Open Web Text)

Max Activating Token Index: 750

Text #11

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1910. Min Act: -0.1700

Data Index: 6643635 (Open Web Text)

Max Activating Token Index: 752

Text #12

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1954. Min Act: -0.1700

Data Index: 3099309 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1918. Min Act: -0.1700

Data Index: 3128713 (Open Web Text)

Max Activating Token Index: 666

Text #14

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1711. Min Act: -0.1700

Data Index: 981927 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1787. Min Act: -0.1700

Data Index: 3143148 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1628. Min Act: -0.1700

Data Index: 174326 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1164. Min Act: -0.1700

Data Index: 6346842 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1191. Min Act: -0.1700

Data Index: 6501096 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.1145. Min Act: -0.1700

Data Index: 156756 (Open Web Text)

Max Activating Token Index: 461