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

Dataset: Open Web Text

Neuron 1804 in Layer 4

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: 6.2118. Min Range: -6.2118

Max Act: 6.2118. Min Act: -0.1700

Data Index: 1771620 (Open Web Text)

Max Activating Token Index: 448

Text #1

Max Range: 6.2118. Min Range: -6.2118

Max Act: 6.0879. Min Act: -0.1700

Data Index: 7831349 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 6.2118. Min Range: -6.2118

Max Act: 6.0049. Min Act: -0.1700

Data Index: 3246170 (Open Web Text)

Max Activating Token Index: 197

Text #3

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9056. Min Act: -0.1700

Data Index: 814936 (Open Web Text)

Max Activating Token Index: 859

Text #4

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9560. Min Act: -0.1700

Data Index: 6089409 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9774. Min Act: -0.1700

Data Index: 3142478 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9597. Min Act: -0.1700

Data Index: 5090250 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9707. Min Act: -0.1700

Data Index: 3951167 (Open Web Text)

Max Activating Token Index: 569

Text #8

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9162. Min Act: -0.1700

Data Index: 2853826 (Open Web Text)

Max Activating Token Index: 186

Text #9

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9083. Min Act: -0.1700

Data Index: 1503150 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.9271. Min Act: -0.1700

Data Index: 5911915 (Open Web Text)

Max Activating Token Index: 761

Text #11

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8416. Min Act: -0.1700

Data Index: 5188108 (Open Web Text)

Max Activating Token Index: 662

Text #12

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8896. Min Act: -0.1700

Data Index: 6089407 (Open Web Text)

Max Activating Token Index: 562

Text #13

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8586. Min Act: -0.1700

Data Index: 3800518 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8901. Min Act: -0.1700

Data Index: 2171618 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8490. Min Act: -0.1700

Data Index: 3073004 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8257. Min Act: -0.1700

Data Index: 4412654 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8087. Min Act: -0.1700

Data Index: 6164525 (Open Web Text)

Max Activating Token Index: 704

Text #18

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.8318. Min Act: -0.1700

Data Index: 7126669 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 6.2118. Min Range: -6.2118

Max Act: 5.7822. Min Act: -0.1700

Data Index: 4691119 (Open Web Text)

Max Activating Token Index: 599