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

Dataset: Open Web Text

Neuron 2090 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: 3.1928. Min Range: -3.1928

Max Act: 3.1928. Min Act: -0.1700

Data Index: 4781223 (Open Web Text)

Max Activating Token Index: 130

Text #1

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.1251. Min Act: -0.1700

Data Index: 3962758 (Open Web Text)

Max Activating Token Index: 261

Text #2

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0996. Min Act: -0.1700

Data Index: 8826722 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0966. Min Act: -0.1700

Data Index: 1470483 (Open Web Text)

Max Activating Token Index: 100

Text #4

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0840. Min Act: -0.1700

Data Index: 6135896 (Open Web Text)

Max Activating Token Index: 385

Text #5

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0836. Min Act: -0.1700

Data Index: 2520566 (Open Web Text)

Max Activating Token Index: 289

Text #6

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0612. Min Act: -0.1700

Data Index: 6685160 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0673. Min Act: -0.1700

Data Index: 3734322 (Open Web Text)

Max Activating Token Index: 83

Text #8

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0645. Min Act: -0.1700

Data Index: 5414001 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0464. Min Act: -0.1700

Data Index: 7590146 (Open Web Text)

Max Activating Token Index: 343

Text #10

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0604. Min Act: -0.1700

Data Index: 86177 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0499. Min Act: -0.1700

Data Index: 3161387 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0509. Min Act: -0.1700

Data Index: 8480920 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0392. Min Act: -0.1700

Data Index: 1665234 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0420. Min Act: -0.1700

Data Index: 6773521 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0386. Min Act: -0.1700

Data Index: 64847 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0307. Min Act: -0.1700

Data Index: 5044235 (Open Web Text)

Max Activating Token Index: 831

Text #17

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0092. Min Act: -0.1700

Data Index: 8157532 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0196. Min Act: -0.1700

Data Index: 3094317 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.1928. Min Range: -3.1928

Max Act: 3.0211. Min Act: -0.1700

Data Index: 599616 (Open Web Text)

Max Activating Token Index: 32