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

Dataset: Open Web Text

Neuron 634 in Layer 6

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: 5.4095. Min Range: -5.4095

Max Act: 5.4095. Min Act: -0.1700

Data Index: 7350359 (Open Web Text)

Max Activating Token Index: 654

Text #1

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.3398. Min Act: -0.1700

Data Index: 6081415 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.2826. Min Act: -0.1700

Data Index: 8182832 (Open Web Text)

Max Activating Token Index: 846

Text #3

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.2624. Min Act: -0.1700

Data Index: 6102172 (Open Web Text)

Max Activating Token Index: 237

Text #4

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.2442. Min Act: -0.1700

Data Index: 5604366 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1889. Min Act: -0.1700

Data Index: 7293979 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.2056. Min Act: -0.1700

Data Index: 5366039 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1654. Min Act: -0.1700

Data Index: 1295121 (Open Web Text)

Max Activating Token Index: 466

Text #8

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1505. Min Act: -0.1700

Data Index: 5119136 (Open Web Text)

Max Activating Token Index: 917

Text #9

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1526. Min Act: -0.1700

Data Index: 4653358 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1480. Min Act: -0.1700

Data Index: 612963 (Open Web Text)

Max Activating Token Index: 808

Text #11

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1206. Min Act: -0.1700

Data Index: 3490328 (Open Web Text)

Max Activating Token Index: 929

Text #12

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.0955. Min Act: -0.1700

Data Index: 3773928 (Open Web Text)

Max Activating Token Index: 873

Text #13

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1048. Min Act: -0.1700

Data Index: 7037443 (Open Web Text)

Max Activating Token Index: 903

Text #14

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.0959. Min Act: -0.1700

Data Index: 4315199 (Open Web Text)

Max Activating Token Index: 364

Text #15

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1250. Min Act: -0.1700

Data Index: 5319281 (Open Web Text)

Max Activating Token Index: 945

Text #16

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.1199. Min Act: -0.1700

Data Index: 5228109 (Open Web Text)

Max Activating Token Index: 751

Text #17

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.0722. Min Act: -0.1700

Data Index: 3699520 (Open Web Text)

Max Activating Token Index: 395

Text #18

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.0653. Min Act: -0.1700

Data Index: 3950716 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 5.4095. Min Range: -5.4095

Max Act: 5.0510. Min Act: -0.1700

Data Index: 3935093 (Open Web Text)

Max Activating Token Index: 651