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

Dataset: Open Web Text

Neuron 2418 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: 4.6817. Min Range: -4.6817

Max Act: 4.6817. Min Act: -0.1700

Data Index: 5103241 (Open Web Text)

Max Activating Token Index: 738

Text #1

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.6109. Min Act: -0.1700

Data Index: 7397094 (Open Web Text)

Max Activating Token Index: 566

Text #2

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.6270. Min Act: -0.1700

Data Index: 1882463 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.6104. Min Act: -0.1700

Data Index: 3889077 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.4742. Min Act: -0.1700

Data Index: 4310003 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.5142. Min Act: -0.1700

Data Index: 2371310 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.4620. Min Act: -0.1700

Data Index: 5215585 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3939. Min Act: -0.1700

Data Index: 1562853 (Open Web Text)

Max Activating Token Index: 120

Text #8

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.4220. Min Act: -0.1700

Data Index: 2838692 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.4101. Min Act: -0.1700

Data Index: 5598944 (Open Web Text)

Max Activating Token Index: 707

Text #10

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.4352. Min Act: -0.1700

Data Index: 6599964 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.4504. Min Act: -0.1700

Data Index: 5052079 (Open Web Text)

Max Activating Token Index: 818

Text #12

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3933. Min Act: -0.1700

Data Index: 7200328 (Open Web Text)

Max Activating Token Index: 1011

Text #13

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3924. Min Act: -0.1700

Data Index: 5842303 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3330. Min Act: -0.1700

Data Index: 1234700 (Open Web Text)

Max Activating Token Index: 64

Text #15

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3591. Min Act: -0.1700

Data Index: 6559531 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3417. Min Act: -0.1700

Data Index: 7492154 (Open Web Text)

Max Activating Token Index: 380

Text #17

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3372. Min Act: -0.1700

Data Index: 2217481 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.3277. Min Act: -0.1700

Data Index: 1909759 (Open Web Text)

Max Activating Token Index: 1018

Text #19

Max Range: 4.6817. Min Range: -4.6817

Max Act: 4.2795. Min Act: -0.1700

Data Index: 7016303 (Open Web Text)

Max Activating Token Index: 382