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

Dataset: Open Web Text

Neuron 388 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: 1.6582. Min Range: -1.6582

Max Act: 1.6582. Min Act: -0.1699

Data Index: 5634649 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6417. Min Act: -0.1564

Data Index: 7633730 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6247. Min Act: -0.1686

Data Index: 7516145 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6339. Min Act: -0.1675

Data Index: 6658469 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6332. Min Act: -0.1698

Data Index: 2381207 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6194. Min Act: -0.1698

Data Index: 316854 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6129. Min Act: -0.1700

Data Index: 4939607 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6111. Min Act: -0.1698

Data Index: 4244230 (Open Web Text)

Max Activating Token Index: 584

Text #8

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5904. Min Act: -0.1700

Data Index: 3593912 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5950. Min Act: -0.1629

Data Index: 977579 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.6072. Min Act: -0.1699

Data Index: 5313172 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5757. Min Act: -0.1593

Data Index: 7802174 (Open Web Text)

Max Activating Token Index: 314

Text #12

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5838. Min Act: -0.1665

Data Index: 5257286 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5883. Min Act: -0.1699

Data Index: 8325439 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5940. Min Act: -0.1678

Data Index: 4747023 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5759. Min Act: -0.1676

Data Index: 1196378 (Open Web Text)

Max Activating Token Index: 592

Text #16

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5722. Min Act: -0.1700

Data Index: 4201468 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5736. Min Act: -0.1674

Data Index: 3829001 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5714. Min Act: -0.1680

Data Index: 6419015 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 1.6582. Min Range: -1.6582

Max Act: 1.5795. Min Act: -0.1698

Data Index: 86470 (Open Web Text)

Max Activating Token Index: 94