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

Dataset: Open Web Text

Neuron 2657 in Layer 1

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: 3.2622. Min Range: -3.2622

Max Act: 3.2622. Min Act: -0.1700

Data Index: 727876 (Open Web Text)

Max Activating Token Index: 652

Text #1

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.2074. Min Act: -0.1700

Data Index: 6860692 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.1756. Min Act: -0.1700

Data Index: 5143291 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.1237. Min Act: -0.1700

Data Index: 7868985 (Open Web Text)

Max Activating Token Index: 544

Text #4

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.1208. Min Act: -0.1700

Data Index: 605826 (Open Web Text)

Max Activating Token Index: 655

Text #5

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.1373. Min Act: -0.1700

Data Index: 4428036 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.1349. Min Act: -0.1700

Data Index: 635918 (Open Web Text)

Max Activating Token Index: 159

Text #7

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.1036. Min Act: -0.1700

Data Index: 2940279 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.1099. Min Act: -0.1700

Data Index: 8249684 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0797. Min Act: -0.1413

Data Index: 3976976 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0802. Min Act: -0.1700

Data Index: 619046 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0869. Min Act: -0.1700

Data Index: 216899 (Open Web Text)

Max Activating Token Index: 54

Text #12

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0633. Min Act: -0.1700

Data Index: 5967321 (Open Web Text)

Max Activating Token Index: 264

Text #13

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0717. Min Act: -0.1700

Data Index: 562188 (Open Web Text)

Max Activating Token Index: 127

Text #14

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0458. Min Act: -0.1700

Data Index: 3607789 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0555. Min Act: -0.1700

Data Index: 2940498 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0550. Min Act: -0.1700

Data Index: 8053526 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0400. Min Act: -0.1700

Data Index: 395598 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0480. Min Act: -0.1700

Data Index: 367966 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 3.2622. Min Range: -3.2622

Max Act: 3.0315. Min Act: -0.1700

Data Index: 1402641 (Open Web Text)

Max Activating Token Index: 241