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

Dataset: Open Web Text

Neuron 1378 in Layer 0

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: 5.7071. Min Range: -5.7071

Max Act: 5.7071. Min Act: -0.1700

Data Index: 5247310 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4969. Min Act: -0.1700

Data Index: 629691 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4894. Min Act: -0.1700

Data Index: 2981362 (Open Web Text)

Max Activating Token Index: 318

Text #3

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4435. Min Act: -0.1700

Data Index: 7545239 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4660. Min Act: -0.1700

Data Index: 2710902 (Open Web Text)

Max Activating Token Index: 848

Text #5

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4849. Min Act: -0.1700

Data Index: 3381764 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4517. Min Act: -0.1700

Data Index: 6354368 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4319. Min Act: -0.1700

Data Index: 7856566 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4038. Min Act: -0.1700

Data Index: 197563 (Open Web Text)

Max Activating Token Index: 168

Text #9

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4220. Min Act: -0.1700

Data Index: 5247311 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.4016. Min Act: -0.1700

Data Index: 1015894 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3726. Min Act: -0.1700

Data Index: 6183887 (Open Web Text)

Max Activating Token Index: 816

Text #12

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3765. Min Act: -0.1700

Data Index: 2035008 (Open Web Text)

Max Activating Token Index: 751

Text #13

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3747. Min Act: -0.1700

Data Index: 69611 (Open Web Text)

Max Activating Token Index: 796

Text #14

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3372. Min Act: -0.1700

Data Index: 4804608 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3301. Min Act: -0.1700

Data Index: 6483170 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3378. Min Act: -0.1700

Data Index: 2949774 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3599. Min Act: -0.1700

Data Index: 928205 (Open Web Text)

Max Activating Token Index: 800

Text #18

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3126. Min Act: -0.1700

Data Index: 865020 (Open Web Text)

Max Activating Token Index: 526

Text #19

Max Range: 5.7071. Min Range: -5.7071

Max Act: 5.3039. Min Act: -0.1700

Data Index: 559868 (Open Web Text)

Max Activating Token Index: 297