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

Dataset: Open Web Text

Neuron 2275 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: 4.2233. Min Range: -4.2233

Max Act: 4.2233. Min Act: -0.1700

Data Index: 3662414 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.7856. Min Act: -0.1700

Data Index: 2882956 (Open Web Text)

Max Activating Token Index: 189

Text #2

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.7927. Min Act: -0.1700

Data Index: 2103721 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.6955. Min Act: -0.1700

Data Index: 873523 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.6662. Min Act: -0.1700

Data Index: 1528514 (Open Web Text)

Max Activating Token Index: 691

Text #5

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.6612. Min Act: -0.1700

Data Index: 5825360 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.6611. Min Act: -0.1700

Data Index: 2115011 (Open Web Text)

Max Activating Token Index: 514

Text #7

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.5798. Min Act: -0.1700

Data Index: 3176695 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.5717. Min Act: -0.1700

Data Index: 7441671 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.5585. Min Act: -0.1700

Data Index: 4389608 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.5633. Min Act: -0.1700

Data Index: 4797582 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.4241. Min Act: -0.1700

Data Index: 2749622 (Open Web Text)

Max Activating Token Index: 189

Text #12

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.5214. Min Act: -0.1700

Data Index: 1959327 (Open Web Text)

Max Activating Token Index: 903

Text #13

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.4546. Min Act: -0.1700

Data Index: 3607874 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.4719. Min Act: -0.1700

Data Index: 8232391 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.5019. Min Act: -0.1700

Data Index: 545716 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.4251. Min Act: -0.1700

Data Index: 5164074 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.4780. Min Act: -0.1700

Data Index: 3439177 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.4427. Min Act: -0.1700

Data Index: 4331920 (Open Web Text)

Max Activating Token Index: 316

Text #19

Max Range: 4.2233. Min Range: -4.2233

Max Act: 3.4457. Min Act: -0.1700

Data Index: 219127 (Open Web Text)

Max Activating Token Index: 804