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

Dataset: Open Web Text

Neuron 1914 in Layer 4

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: 5.0801. Min Range: -5.0801

Max Act: 5.0801. Min Act: -0.1700

Data Index: 1897403 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9737. Min Act: -0.1700

Data Index: 8426448 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9172. Min Act: -0.1700

Data Index: 2993339 (Open Web Text)

Max Activating Token Index: 650

Text #3

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.9205. Min Act: -0.1700

Data Index: 924196 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8890. Min Act: -0.1700

Data Index: 7408411 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8656. Min Act: -0.1700

Data Index: 5910778 (Open Web Text)

Max Activating Token Index: 600

Text #6

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8629. Min Act: -0.1700

Data Index: 1939749 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8592. Min Act: -0.1700

Data Index: 7797473 (Open Web Text)

Max Activating Token Index: 868

Text #8

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8353. Min Act: -0.1700

Data Index: 4001603 (Open Web Text)

Max Activating Token Index: 571

Text #9

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7798. Min Act: -0.1700

Data Index: 1184633 (Open Web Text)

Max Activating Token Index: 942

Text #10

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.8197. Min Act: -0.1700

Data Index: 8656770 (Open Web Text)

Max Activating Token Index: 387

Text #11

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7566. Min Act: -0.1700

Data Index: 4356383 (Open Web Text)

Max Activating Token Index: 143

Text #12

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7363. Min Act: -0.1700

Data Index: 2342323 (Open Web Text)

Max Activating Token Index: 839

Text #13

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.6999. Min Act: -0.1700

Data Index: 6218650 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7263. Min Act: -0.1700

Data Index: 1617473 (Open Web Text)

Max Activating Token Index: 518

Text #15

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7601. Min Act: -0.1700

Data Index: 325340 (Open Web Text)

Max Activating Token Index: 862

Text #16

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7484. Min Act: -0.1700

Data Index: 4190491 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7122. Min Act: -0.1700

Data Index: 238801 (Open Web Text)

Max Activating Token Index: 690

Text #18

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.7233. Min Act: -0.1700

Data Index: 4991465 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 5.0801. Min Range: -5.0801

Max Act: 4.6822. Min Act: -0.1700

Data Index: 2554922 (Open Web Text)

Max Activating Token Index: 629