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

Dataset: Open Web Text

Neuron 355 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: 3.7416. Min Range: -3.7416

Max Act: 3.7076. Min Act: -0.1700

Data Index: 1460915 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.7416. Min Act: -0.1700

Data Index: 3998058 (Open Web Text)

Max Activating Token Index: 151

Text #2

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.7141. Min Act: -0.1700

Data Index: 6751466 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.7244. Min Act: -0.1700

Data Index: 3035956 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6903. Min Act: -0.1700

Data Index: 2857624 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.7035. Min Act: -0.1700

Data Index: 6012574 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6917. Min Act: -0.1700

Data Index: 8075358 (Open Web Text)

Max Activating Token Index: 208

Text #7

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6953. Min Act: -0.1700

Data Index: 6839780 (Open Web Text)

Max Activating Token Index: 995

Text #8

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6719. Min Act: -0.1700

Data Index: 6100027 (Open Web Text)

Max Activating Token Index: 954

Text #9

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6689. Min Act: -0.1700

Data Index: 8210057 (Open Web Text)

Max Activating Token Index: 371

Text #10

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6494. Min Act: -0.1700

Data Index: 7481407 (Open Web Text)

Max Activating Token Index: 439

Text #11

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6588. Min Act: -0.1700

Data Index: 4603496 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6231. Min Act: -0.1700

Data Index: 1619830 (Open Web Text)

Max Activating Token Index: 897

Text #13

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6236. Min Act: -0.1700

Data Index: 4916116 (Open Web Text)

Max Activating Token Index: 452

Text #14

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6187. Min Act: -0.1700

Data Index: 4715951 (Open Web Text)

Max Activating Token Index: 580

Text #15

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6014. Min Act: -0.1700

Data Index: 639523 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6043. Min Act: -0.1700

Data Index: 3324401 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.5976. Min Act: -0.1700

Data Index: 3703175 (Open Web Text)

Max Activating Token Index: 723

Text #18

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.6047. Min Act: -0.1700

Data Index: 3075414 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 3.7416. Min Range: -3.7416

Max Act: 3.5884. Min Act: -0.1700

Data Index: 3025777 (Open Web Text)

Max Activating Token Index: 832