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

Dataset: Open Web Text

Neuron 2837 in Layer 1

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: 1.6338. Min Range: -1.6338

Max Act: 1.6338. Min Act: -0.1700

Data Index: 7976838 (Open Web Text)

Max Activating Token Index: 579

Text #1

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6285. Min Act: -0.1699

Data Index: 3846564 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6226. Min Act: -0.1698

Data Index: 501510 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6104. Min Act: -0.1700

Data Index: 5778319 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6096. Min Act: -0.1700

Data Index: 239078 (Open Web Text)

Max Activating Token Index: 81

Text #5

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6154. Min Act: -0.1696

Data Index: 4447893 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6176. Min Act: -0.1700

Data Index: 6083649 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6019. Min Act: -0.1700

Data Index: 3934001 (Open Web Text)

Max Activating Token Index: 432

Text #8

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6096. Min Act: -0.1700

Data Index: 7858162 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.6017. Min Act: -0.1700

Data Index: 3294061 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5934. Min Act: -0.1700

Data Index: 6276120 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5951. Min Act: -0.1700

Data Index: 689160 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5968. Min Act: -0.1700

Data Index: 4342753 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5869. Min Act: -0.1700

Data Index: 1513198 (Open Web Text)

Max Activating Token Index: 354

Text #14

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5900. Min Act: -0.1700

Data Index: 963950 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5914. Min Act: -0.1700

Data Index: 5212016 (Open Web Text)

Max Activating Token Index: 899

Text #16

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5845. Min Act: -0.1700

Data Index: 1140292 (Open Web Text)

Max Activating Token Index: 30

Text #17

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5881. Min Act: -0.1700

Data Index: 1143395 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5820. Min Act: -0.1694

Data Index: 4079511 (Open Web Text)

Max Activating Token Index: 499

Text #19

Max Range: 1.6338. Min Range: -1.6338

Max Act: 1.5817. Min Act: -0.1700

Data Index: 3601128 (Open Web Text)

Max Activating Token Index: 653