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

Dataset: Open Web Text

Neuron 808 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: 3.0764. Min Range: -3.0764

Max Act: 3.0764. Min Act: -0.1700

Data Index: 6693197 (Open Web Text)

Max Activating Token Index: 244

Text #1

Max Range: 3.0764. Min Range: -3.0764

Max Act: 3.0010. Min Act: -0.1700

Data Index: 6304948 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9598. Min Act: -0.1700

Data Index: 6646817 (Open Web Text)

Max Activating Token Index: 796

Text #3

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9111. Min Act: -0.1700

Data Index: 4077370 (Open Web Text)

Max Activating Token Index: 399

Text #4

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9433. Min Act: -0.1700

Data Index: 8720986 (Open Web Text)

Max Activating Token Index: 682

Text #5

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9245. Min Act: -0.1700

Data Index: 620559 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8657. Min Act: -0.1700

Data Index: 6646815 (Open Web Text)

Max Activating Token Index: 697

Text #7

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9029. Min Act: -0.1700

Data Index: 6947911 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8690. Min Act: -0.1700

Data Index: 1089292 (Open Web Text)

Max Activating Token Index: 700

Text #9

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8802. Min Act: -0.1700

Data Index: 1089293 (Open Web Text)

Max Activating Token Index: 397

Text #10

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8757. Min Act: -0.1700

Data Index: 8157218 (Open Web Text)

Max Activating Token Index: 102

Text #11

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8415. Min Act: -0.1700

Data Index: 1089294 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8525. Min Act: -0.1700

Data Index: 7123755 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8649. Min Act: -0.1700

Data Index: 4791114 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8600. Min Act: -0.1700

Data Index: 6646816 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8542. Min Act: -0.1700

Data Index: 7295486 (Open Web Text)

Max Activating Token Index: 792

Text #16

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8525. Min Act: -0.1700

Data Index: 1276649 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8375. Min Act: -0.1700

Data Index: 1276669 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8331. Min Act: -0.1700

Data Index: 2308727 (Open Web Text)

Max Activating Token Index: 815

Text #19

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.8330. Min Act: -0.1700

Data Index: 2417266 (Open Web Text)

Max Activating Token Index: 375