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

Dataset: Open Web Text

Neuron 522 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: 3.6363. Min Range: -3.6363

Max Act: 3.6248. Min Act: -0.1700

Data Index: 4562705 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.6363. Min Act: -0.1700

Data Index: 4843959 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5673. Min Act: -0.1700

Data Index: 8778935 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5600. Min Act: -0.1700

Data Index: 8491797 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5448. Min Act: -0.1700

Data Index: 386097 (Open Web Text)

Max Activating Token Index: 738

Text #5

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5268. Min Act: -0.1700

Data Index: 4059813 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5337. Min Act: -0.1700

Data Index: 4567784 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5239. Min Act: -0.1700

Data Index: 142197 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5097. Min Act: -0.1700

Data Index: 5759759 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5120. Min Act: -0.1700

Data Index: 8491796 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5199. Min Act: -0.1700

Data Index: 8029145 (Open Web Text)

Max Activating Token Index: 253

Text #11

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4923. Min Act: -0.1700

Data Index: 7778508 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4892. Min Act: -0.1700

Data Index: 7505853 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4953. Min Act: -0.1700

Data Index: 6445638 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4968. Min Act: -0.1700

Data Index: 4447293 (Open Web Text)

Max Activating Token Index: 802

Text #15

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5019. Min Act: -0.1700

Data Index: 762530 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5077. Min Act: -0.1700

Data Index: 6111409 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5053. Min Act: -0.1700

Data Index: 2851142 (Open Web Text)

Max Activating Token Index: 672

Text #18

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4676. Min Act: -0.1700

Data Index: 5494721 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4822. Min Act: -0.1700

Data Index: 5743162 (Open Web Text)

Max Activating Token Index: 45