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

Dataset: Open Web Text

Neuron 2353 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: 4.9077. Min Range: -4.9077

Max Act: 4.9077. Min Act: -0.1700

Data Index: 8786120 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.8146. Min Act: -0.1700

Data Index: 366517 (Open Web Text)

Max Activating Token Index: 668

Text #2

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.7192. Min Act: -0.1700

Data Index: 8299963 (Open Web Text)

Max Activating Token Index: 806

Text #3

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6971. Min Act: -0.1700

Data Index: 6315839 (Open Web Text)

Max Activating Token Index: 718

Text #4

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6743. Min Act: -0.1700

Data Index: 896558 (Open Web Text)

Max Activating Token Index: 1012

Text #5

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6742. Min Act: -0.1700

Data Index: 4427861 (Open Web Text)

Max Activating Token Index: 552

Text #6

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6742. Min Act: -0.1700

Data Index: 7294284 (Open Web Text)

Max Activating Token Index: 645

Text #7

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6627. Min Act: -0.1700

Data Index: 1358209 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6187. Min Act: -0.1700

Data Index: 2838360 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6201. Min Act: -0.1700

Data Index: 4677086 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6293. Min Act: -0.1700

Data Index: 3659708 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6381. Min Act: -0.1700

Data Index: 4323924 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6130. Min Act: -0.1700

Data Index: 8633782 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6123. Min Act: -0.1700

Data Index: 7920777 (Open Web Text)

Max Activating Token Index: 190

Text #14

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6136. Min Act: -0.1700

Data Index: 2513177 (Open Web Text)

Max Activating Token Index: 66

Text #15

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6175. Min Act: -0.1700

Data Index: 8786119 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.6029. Min Act: -0.1700

Data Index: 7003986 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.5971. Min Act: -0.1700

Data Index: 238880 (Open Web Text)

Max Activating Token Index: 987

Text #18

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.5798. Min Act: -0.1700

Data Index: 1443365 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 4.9077. Min Range: -4.9077

Max Act: 4.5811. Min Act: -0.1700

Data Index: 8054109 (Open Web Text)

Max Activating Token Index: 52