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

Dataset: Open Web Text

Neuron 2368 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: 4.0759. Min Range: -4.0759

Max Act: 4.0759. Min Act: -0.1700

Data Index: 8657388 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 4.0759. Min Range: -4.0759

Max Act: 4.0540. Min Act: -0.1700

Data Index: 4026091 (Open Web Text)

Max Activating Token Index: 557

Text #2

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.9731. Min Act: -0.1700

Data Index: 4405861 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8953. Min Act: -0.1700

Data Index: 6877223 (Open Web Text)

Max Activating Token Index: 437

Text #4

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8592. Min Act: -0.1700

Data Index: 3832754 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8633. Min Act: -0.1700

Data Index: 693742 (Open Web Text)

Max Activating Token Index: 836

Text #6

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8646. Min Act: -0.1700

Data Index: 1209199 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8678. Min Act: -0.1700

Data Index: 457070 (Open Web Text)

Max Activating Token Index: 364

Text #8

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8086. Min Act: -0.1700

Data Index: 5713806 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8346. Min Act: -0.1700

Data Index: 2389614 (Open Web Text)

Max Activating Token Index: 218

Text #10

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8265. Min Act: -0.1700

Data Index: 4116839 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8167. Min Act: -0.1700

Data Index: 2072855 (Open Web Text)

Max Activating Token Index: 343

Text #12

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8126. Min Act: -0.1700

Data Index: 8646099 (Open Web Text)

Max Activating Token Index: 242

Text #13

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.7940. Min Act: -0.1700

Data Index: 6355529 (Open Web Text)

Max Activating Token Index: 902

Text #14

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.8244. Min Act: -0.1700

Data Index: 1888378 (Open Web Text)

Max Activating Token Index: 749

Text #15

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.7936. Min Act: -0.1700

Data Index: 335618 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.7827. Min Act: -0.1700

Data Index: 2400863 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.7783. Min Act: -0.1700

Data Index: 4439866 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.7735. Min Act: -0.1700

Data Index: 5252986 (Open Web Text)

Max Activating Token Index: 335

Text #19

Max Range: 4.0759. Min Range: -4.0759

Max Act: 3.7866. Min Act: -0.1700

Data Index: 6954930 (Open Web Text)

Max Activating Token Index: 470