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

Dataset: Open Web Text

Neuron 1094 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: 4.7057. Min Range: -4.7057

Max Act: 4.7057. Min Act: -0.1700

Data Index: 4220096 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.5066. Min Act: -0.1700

Data Index: 5648381 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.5052. Min Act: -0.1700

Data Index: 1883621 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.4909. Min Act: -0.1700

Data Index: 2852743 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.4520. Min Act: -0.1700

Data Index: 4269496 (Open Web Text)

Max Activating Token Index: 851

Text #5

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.4737. Min Act: -0.1700

Data Index: 2237842 (Open Web Text)

Max Activating Token Index: 302

Text #6

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.4297. Min Act: -0.1700

Data Index: 2601559 (Open Web Text)

Max Activating Token Index: 468

Text #7

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.4390. Min Act: -0.1700

Data Index: 4774841 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.4025. Min Act: -0.1700

Data Index: 4638194 (Open Web Text)

Max Activating Token Index: 112

Text #9

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.4145. Min Act: -0.1700

Data Index: 8245014 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3570. Min Act: -0.1700

Data Index: 744211 (Open Web Text)

Max Activating Token Index: 193

Text #11

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3616. Min Act: -0.1700

Data Index: 3586349 (Open Web Text)

Max Activating Token Index: 58

Text #12

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3175. Min Act: -0.1700

Data Index: 1487313 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3109. Min Act: -0.1700

Data Index: 3069393 (Open Web Text)

Max Activating Token Index: 77

Text #14

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3013. Min Act: -0.1700

Data Index: 1169920 (Open Web Text)

Max Activating Token Index: 700

Text #15

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3095. Min Act: -0.1700

Data Index: 3228430 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3295. Min Act: -0.1700

Data Index: 800348 (Open Web Text)

Max Activating Token Index: 822

Text #17

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3435. Min Act: -0.1700

Data Index: 3576836 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.2744. Min Act: -0.1700

Data Index: 1364333 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 4.7057. Min Range: -4.7057

Max Act: 4.3238. Min Act: -0.1700

Data Index: 736744 (Open Web Text)

Max Activating Token Index: 224