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

Dataset: Open Web Text

Neuron 1792 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: 4.2670. Min Range: -4.2670

Max Act: 4.2670. Min Act: -0.1700

Data Index: 7992707 (Open Web Text)

Max Activating Token Index: 378

Text #1

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.2283. Min Act: -0.1700

Data Index: 222495 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1986. Min Act: -0.1700

Data Index: 8604592 (Open Web Text)

Max Activating Token Index: 439

Text #3

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1862. Min Act: -0.1700

Data Index: 8305448 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1382. Min Act: -0.1700

Data Index: 2347781 (Open Web Text)

Max Activating Token Index: 320

Text #5

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1009. Min Act: -0.1700

Data Index: 3985005 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1052. Min Act: -0.1700

Data Index: 7744112 (Open Web Text)

Max Activating Token Index: 50

Text #7

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1616. Min Act: -0.1700

Data Index: 5854861 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1053. Min Act: -0.1700

Data Index: 1799863 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1530. Min Act: -0.1700

Data Index: 4124943 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.1584. Min Act: -0.1700

Data Index: 2474553 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0491. Min Act: -0.1700

Data Index: 3456958 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0496. Min Act: -0.1700

Data Index: 1676817 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0754. Min Act: -0.1700

Data Index: 1849356 (Open Web Text)

Max Activating Token Index: 378

Text #14

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0227. Min Act: -0.1700

Data Index: 7641523 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0549. Min Act: -0.1700

Data Index: 7134938 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0108. Min Act: -0.1700

Data Index: 3210157 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0669. Min Act: -0.1700

Data Index: 8283980 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 4.2670. Min Range: -4.2670

Max Act: 4.0730. Min Act: -0.1700

Data Index: 2040216 (Open Web Text)

Max Activating Token Index: 249

Text #19

Max Range: 4.2670. Min Range: -4.2670

Max Act: 3.9988. Min Act: -0.1700

Data Index: 4484263 (Open Web Text)

Max Activating Token Index: 76