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

Dataset: Open Web Text

Neuron 370 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: 4.3098. Min Range: -4.3098

Max Act: 4.3098. Min Act: -0.1700

Data Index: 7543138 (Open Web Text)

Max Activating Token Index: 849

Text #1

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.2121. Min Act: -0.1700

Data Index: 8822417 (Open Web Text)

Max Activating Token Index: 748

Text #2

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.1557. Min Act: -0.1700

Data Index: 5449032 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.1352. Min Act: -0.1700

Data Index: 5883428 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0622. Min Act: -0.1700

Data Index: 7310856 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.1182. Min Act: -0.1700

Data Index: 901111 (Open Web Text)

Max Activating Token Index: 398

Text #6

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0933. Min Act: -0.1700

Data Index: 7775284 (Open Web Text)

Max Activating Token Index: 703

Text #7

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0568. Min Act: -0.1700

Data Index: 4616432 (Open Web Text)

Max Activating Token Index: 900

Text #8

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0344. Min Act: -0.1700

Data Index: 6051032 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0067. Min Act: -0.1700

Data Index: 5475439 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0338. Min Act: -0.1700

Data Index: 36763 (Open Web Text)

Max Activating Token Index: 793

Text #11

Max Range: 4.3098. Min Range: -4.3098

Max Act: 3.9977. Min Act: -0.1700

Data Index: 4336328 (Open Web Text)

Max Activating Token Index: 363

Text #12

Max Range: 4.3098. Min Range: -4.3098

Max Act: 3.9806. Min Act: -0.1700

Data Index: 1054385 (Open Web Text)

Max Activating Token Index: 171

Text #13

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0133. Min Act: -0.1700

Data Index: 5834437 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 4.3098. Min Range: -4.3098

Max Act: 4.0102. Min Act: -0.1700

Data Index: 3533 (Open Web Text)

Max Activating Token Index: 615

Text #15

Max Range: 4.3098. Min Range: -4.3098

Max Act: 3.9987. Min Act: -0.1700

Data Index: 2009063 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 4.3098. Min Range: -4.3098

Max Act: 3.9618. Min Act: -0.1700

Data Index: 3010912 (Open Web Text)

Max Activating Token Index: 469

Text #17

Max Range: 4.3098. Min Range: -4.3098

Max Act: 3.9751. Min Act: -0.1700

Data Index: 1778310 (Open Web Text)

Max Activating Token Index: 334

Text #18

Max Range: 4.3098. Min Range: -4.3098

Max Act: 3.9640. Min Act: -0.1700

Data Index: 6330143 (Open Web Text)

Max Activating Token Index: 662

Text #19

Max Range: 4.3098. Min Range: -4.3098

Max Act: 3.9683. Min Act: -0.1700

Data Index: 7121501 (Open Web Text)

Max Activating Token Index: 999