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

Dataset: Open Web Text

Neuron 436 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: 2.5363. Min Range: -2.5363

Max Act: 2.5363. Min Act: -0.1700

Data Index: 813515 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.5363. Min Act: -0.1700

Data Index: 7190052 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.5363. Min Act: -0.1700

Data Index: 3384706 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.5363. Min Act: -0.1700

Data Index: 1030099 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.5003. Min Act: -0.1700

Data Index: 518195 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.5077. Min Act: -0.1700

Data Index: 3676522 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4837. Min Act: -0.1700

Data Index: 8133912 (Open Web Text)

Max Activating Token Index: 472

Text #7

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4942. Min Act: -0.1700

Data Index: 5733317 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4580. Min Act: -0.1700

Data Index: 1522048 (Open Web Text)

Max Activating Token Index: 159

Text #9

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4703. Min Act: -0.1700

Data Index: 1638264 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4636. Min Act: -0.1700

Data Index: 4949566 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4596. Min Act: -0.1700

Data Index: 677722 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4471. Min Act: -0.1700

Data Index: 152690 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4441. Min Act: -0.1700

Data Index: 3580524 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4446. Min Act: -0.1700

Data Index: 1638267 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4286. Min Act: -0.1700

Data Index: 1877878 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4458. Min Act: -0.1700

Data Index: 6836552 (Open Web Text)

Max Activating Token Index: 60

Text #17

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4476. Min Act: -0.1700

Data Index: 6803077 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4381. Min Act: -0.1700

Data Index: 5129969 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4365. Min Act: -0.1700

Data Index: 2945752 (Open Web Text)

Max Activating Token Index: 9