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

Dataset: Open Web Text

Neuron 280 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: 4.6867. Min Range: -4.6867

Max Act: 4.6430. Min Act: -0.1700

Data Index: 3398355 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.6867. Min Act: -0.1700

Data Index: 6106906 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.5528. Min Act: -0.1700

Data Index: 967321 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.5667. Min Act: -0.1700

Data Index: 3322847 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.5089. Min Act: -0.1700

Data Index: 4900874 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4592. Min Act: -0.1700

Data Index: 2082438 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4938. Min Act: -0.1700

Data Index: 7579834 (Open Web Text)

Max Activating Token Index: 483

Text #7

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4977. Min Act: -0.1700

Data Index: 5907594 (Open Web Text)

Max Activating Token Index: 830

Text #8

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4578. Min Act: -0.1700

Data Index: 350163 (Open Web Text)

Max Activating Token Index: 844

Text #9

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4708. Min Act: -0.1700

Data Index: 5118051 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4817. Min Act: -0.1700

Data Index: 590556 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4480. Min Act: -0.1700

Data Index: 1462679 (Open Web Text)

Max Activating Token Index: 69

Text #12

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4350. Min Act: -0.1700

Data Index: 852271 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4477. Min Act: -0.1700

Data Index: 1886202 (Open Web Text)

Max Activating Token Index: 956

Text #14

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4234. Min Act: -0.1700

Data Index: 3048203 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4389. Min Act: -0.1700

Data Index: 7286145 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4159. Min Act: -0.1700

Data Index: 1557689 (Open Web Text)

Max Activating Token Index: 243

Text #17

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4084. Min Act: -0.1700

Data Index: 1087408 (Open Web Text)

Max Activating Token Index: 587

Text #18

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.4326. Min Act: -0.1700

Data Index: 7907162 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.3914. Min Act: -0.1700

Data Index: 5197014 (Open Web Text)

Max Activating Token Index: 917