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

Dataset: Open Web Text

Neuron 664 in Layer 6

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: 5.2669. Min Range: -5.2669

Max Act: 5.2669. Min Act: -0.1700

Data Index: 1745381 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.1159. Min Act: -0.1700

Data Index: 7173297 (Open Web Text)

Max Activating Token Index: 729

Text #2

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.1020. Min Act: -0.1700

Data Index: 3246391 (Open Web Text)

Max Activating Token Index: 92

Text #3

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.0812. Min Act: -0.1700

Data Index: 7129029 (Open Web Text)

Max Activating Token Index: 691

Text #4

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.0576. Min Act: -0.1700

Data Index: 521131 (Open Web Text)

Max Activating Token Index: 805

Text #5

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.0138. Min Act: -0.1700

Data Index: 5296874 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 5.2669. Min Range: -5.2669

Max Act: 5.0080. Min Act: -0.1700

Data Index: 7876569 (Open Web Text)

Max Activating Token Index: 65

Text #7

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9871. Min Act: -0.1700

Data Index: 7382546 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9277. Min Act: -0.1700

Data Index: 6478768 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9359. Min Act: -0.1700

Data Index: 117840 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9536. Min Act: -0.1700

Data Index: 618595 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9031. Min Act: -0.1700

Data Index: 2362814 (Open Web Text)

Max Activating Token Index: 972

Text #12

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9330. Min Act: -0.1700

Data Index: 4977177 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8987. Min Act: -0.1700

Data Index: 2783831 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.9121. Min Act: -0.1700

Data Index: 7958404 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8974. Min Act: -0.1700

Data Index: 3317754 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8278. Min Act: -0.1700

Data Index: 7270517 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8525. Min Act: -0.1700

Data Index: 2838566 (Open Web Text)

Max Activating Token Index: 221

Text #18

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8347. Min Act: -0.1700

Data Index: 2114821 (Open Web Text)

Max Activating Token Index: 703

Text #19

Max Range: 5.2669. Min Range: -5.2669

Max Act: 4.8529. Min Act: -0.1700

Data Index: 5212158 (Open Web Text)

Max Activating Token Index: 662