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

Dataset: Open Web Text

Neuron 569 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: 3.8867. Min Range: -3.8867

Max Act: 3.8867. Min Act: -0.1700

Data Index: 4779208 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.8050. Min Act: -0.1700

Data Index: 2985252 (Open Web Text)

Max Activating Token Index: 112

Text #2

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7651. Min Act: -0.1700

Data Index: 1349378 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7627. Min Act: -0.1700

Data Index: 4349730 (Open Web Text)

Max Activating Token Index: 893

Text #4

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7924. Min Act: -0.1700

Data Index: 4667466 (Open Web Text)

Max Activating Token Index: 551

Text #5

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7691. Min Act: -0.1700

Data Index: 650552 (Open Web Text)

Max Activating Token Index: 500

Text #6

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7523. Min Act: -0.1700

Data Index: 4879223 (Open Web Text)

Max Activating Token Index: 734

Text #7

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7535. Min Act: -0.1700

Data Index: 3364423 (Open Web Text)

Max Activating Token Index: 224

Text #8

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7562. Min Act: -0.1700

Data Index: 4297767 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7667. Min Act: -0.1700

Data Index: 446594 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7580. Min Act: -0.1700

Data Index: 7450356 (Open Web Text)

Max Activating Token Index: 162

Text #11

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7114. Min Act: -0.1700

Data Index: 6800182 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7263. Min Act: -0.1700

Data Index: 5288122 (Open Web Text)

Max Activating Token Index: 998

Text #13

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7267. Min Act: -0.1700

Data Index: 1206018 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7218. Min Act: -0.1700

Data Index: 1015247 (Open Web Text)

Max Activating Token Index: 580

Text #15

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7072. Min Act: -0.1700

Data Index: 658879 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7182. Min Act: -0.1700

Data Index: 963935 (Open Web Text)

Max Activating Token Index: 663

Text #17

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7341. Min Act: -0.1700

Data Index: 6592632 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.7145. Min Act: -0.1700

Data Index: 5926175 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.8867. Min Range: -3.8867

Max Act: 3.6706. Min Act: -0.1700

Data Index: 5387055 (Open Web Text)

Max Activating Token Index: 916