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

Dataset: Open Web Text

Neuron 2551 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: 3.9284. Min Range: -3.9284

Max Act: 3.9284. Min Act: -0.1700

Data Index: 6555004 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.9157. Min Act: -0.1700

Data Index: 8038861 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8990. Min Act: -0.1700

Data Index: 5256469 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8827. Min Act: -0.1700

Data Index: 5689407 (Open Web Text)

Max Activating Token Index: 643

Text #4

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8990. Min Act: -0.1700

Data Index: 3463593 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8990. Min Act: -0.1700

Data Index: 6945485 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8990. Min Act: -0.1700

Data Index: 3472124 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8748. Min Act: -0.1700

Data Index: 1521542 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8990. Min Act: -0.1700

Data Index: 299878 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8486. Min Act: -0.1700

Data Index: 5493936 (Open Web Text)

Max Activating Token Index: 121

Text #10

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8571. Min Act: -0.1700

Data Index: 940670 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8613. Min Act: -0.1700

Data Index: 2475794 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8477. Min Act: -0.1700

Data Index: 3241786 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8228. Min Act: -0.1700

Data Index: 4576950 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8320. Min Act: -0.1700

Data Index: 4603002 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8175. Min Act: -0.1700

Data Index: 375804 (Open Web Text)

Max Activating Token Index: 684

Text #16

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8320. Min Act: -0.1700

Data Index: 2122782 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8516. Min Act: -0.1700

Data Index: 564491 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8320. Min Act: -0.1700

Data Index: 2614602 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.9284. Min Range: -3.9284

Max Act: 3.8254. Min Act: -0.1700

Data Index: 4613718 (Open Web Text)

Max Activating Token Index: 635