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

Dataset: Open Web Text

Neuron 2429 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: 5.1951. Min Range: -5.1951

Max Act: 5.1951. Min Act: -0.1700

Data Index: 1144718 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 5.1951. Min Range: -5.1951

Max Act: 5.1609. Min Act: -0.1700

Data Index: 2236190 (Open Web Text)

Max Activating Token Index: 849

Text #2

Max Range: 5.1951. Min Range: -5.1951

Max Act: 5.1064. Min Act: -0.1700

Data Index: 1858342 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 5.1951. Min Range: -5.1951

Max Act: 5.0525. Min Act: -0.1700

Data Index: 3766954 (Open Web Text)

Max Activating Token Index: 338

Text #4

Max Range: 5.1951. Min Range: -5.1951

Max Act: 5.0059. Min Act: -0.1700

Data Index: 2640062 (Open Web Text)

Max Activating Token Index: 913

Text #5

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.9689. Min Act: -0.1700

Data Index: 4672326 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.9102. Min Act: -0.1700

Data Index: 762593 (Open Web Text)

Max Activating Token Index: 463

Text #7

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.9189. Min Act: -0.1700

Data Index: 669390 (Open Web Text)

Max Activating Token Index: 95

Text #8

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.9151. Min Act: -0.1700

Data Index: 452276 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8994. Min Act: -0.1700

Data Index: 1833799 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8733. Min Act: -0.1700

Data Index: 6698229 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8410. Min Act: -0.1700

Data Index: 7998763 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8804. Min Act: -0.1700

Data Index: 1805843 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8340. Min Act: -0.1700

Data Index: 5661965 (Open Web Text)

Max Activating Token Index: 769

Text #14

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8546. Min Act: -0.1700

Data Index: 5428908 (Open Web Text)

Max Activating Token Index: 895

Text #15

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8609. Min Act: -0.1700

Data Index: 1387532 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8058. Min Act: -0.1700

Data Index: 5538775 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8507. Min Act: -0.1700

Data Index: 2670297 (Open Web Text)

Max Activating Token Index: 484

Text #18

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.8544. Min Act: -0.1700

Data Index: 4069357 (Open Web Text)

Max Activating Token Index: 621

Text #19

Max Range: 5.1951. Min Range: -5.1951

Max Act: 4.7937. Min Act: -0.1700

Data Index: 2786867 (Open Web Text)

Max Activating Token Index: 258