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

Dataset: Open Web Text

Neuron 363 in Layer 5

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: 5.9331. Min Range: -5.9331

Max Act: 5.8587. Min Act: -0.1700

Data Index: 4215071 (Open Web Text)

Max Activating Token Index: 889

Text #1

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.9331. Min Act: -0.1700

Data Index: 4464766 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.8440. Min Act: -0.1700

Data Index: 5637047 (Open Web Text)

Max Activating Token Index: 283

Text #3

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.8206. Min Act: -0.1700

Data Index: 4708146 (Open Web Text)

Max Activating Token Index: 225

Text #4

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.8577. Min Act: -0.1700

Data Index: 4515005 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.8296. Min Act: -0.1700

Data Index: 5416699 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7796. Min Act: -0.1700

Data Index: 5674532 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.8215. Min Act: -0.1700

Data Index: 2066420 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7637. Min Act: -0.1700

Data Index: 7764827 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7681. Min Act: -0.1700

Data Index: 4574304 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7945. Min Act: -0.1700

Data Index: 1832311 (Open Web Text)

Max Activating Token Index: 766

Text #11

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7605. Min Act: -0.1700

Data Index: 6185782 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7400. Min Act: -0.1700

Data Index: 5276449 (Open Web Text)

Max Activating Token Index: 247

Text #13

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7236. Min Act: -0.1700

Data Index: 5211553 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7095. Min Act: -0.1700

Data Index: 3732120 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7117. Min Act: -0.1700

Data Index: 3807201 (Open Web Text)

Max Activating Token Index: 212

Text #16

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7430. Min Act: -0.1700

Data Index: 3303887 (Open Web Text)

Max Activating Token Index: 255

Text #17

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.7507. Min Act: -0.1700

Data Index: 1149841 (Open Web Text)

Max Activating Token Index: 267

Text #18

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.6392. Min Act: -0.1700

Data Index: 148344 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 5.9331. Min Range: -5.9331

Max Act: 5.6758. Min Act: -0.1700

Data Index: 4007740 (Open Web Text)

Max Activating Token Index: 267