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

Dataset: Open Web Text

Neuron 628 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: 3.4070. Min Range: -3.4070

Max Act: 3.4070. Min Act: -0.1700

Data Index: 2207369 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.3771. Min Act: -0.1700

Data Index: 3988606 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.2398. Min Act: -0.1700

Data Index: 3320422 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.1759. Min Act: -0.1700

Data Index: 6281976 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.0904. Min Act: -0.1700

Data Index: 4858013 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.0661. Min Act: -0.1700

Data Index: 2379257 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.0437. Min Act: -0.1700

Data Index: 2360058 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.0390. Min Act: -0.1700

Data Index: 8170467 (Open Web Text)

Max Activating Token Index: 359

Text #8

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.0427. Min Act: -0.1700

Data Index: 5521570 (Open Web Text)

Max Activating Token Index: 110

Text #9

Max Range: 3.4070. Min Range: -3.4070

Max Act: 3.0135. Min Act: -0.1700

Data Index: 3802820 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9767. Min Act: -0.1700

Data Index: 7293179 (Open Web Text)

Max Activating Token Index: 420

Text #11

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9646. Min Act: -0.1700

Data Index: 2685077 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9589. Min Act: -0.1700

Data Index: 4154415 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9377. Min Act: -0.1700

Data Index: 4569070 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9418. Min Act: -0.1700

Data Index: 6338809 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9531. Min Act: -0.1700

Data Index: 194449 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9348. Min Act: -0.1700

Data Index: 364487 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9254. Min Act: -0.1700

Data Index: 8457619 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9228. Min Act: -0.1700

Data Index: 7599873 (Open Web Text)

Max Activating Token Index: 227

Text #19

Max Range: 3.4070. Min Range: -3.4070

Max Act: 2.9006. Min Act: -0.1700

Data Index: 4513878 (Open Web Text)

Max Activating Token Index: 9