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

Dataset: Open Web Text

Neuron 2106 in Layer 2

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: 3.1624. Min Range: -3.1624

Max Act: 3.1624. Min Act: -0.1700

Data Index: 922706 (Open Web Text)

Max Activating Token Index: 210

Text #1

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1358. Min Act: -0.1700

Data Index: 7043441 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1110. Min Act: -0.1700

Data Index: 1244054 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1209709 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1750710 (Open Web Text)

Max Activating Token Index: 494

Text #5

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0894. Min Act: -0.1700

Data Index: 8362529 (Open Web Text)

Max Activating Token Index: 711

Text #6

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0942. Min Act: -0.1700

Data Index: 2589931 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0888. Min Act: -0.1700

Data Index: 4428768 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0807. Min Act: -0.1700

Data Index: 289162 (Open Web Text)

Max Activating Token Index: 196

Text #9

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0666. Min Act: -0.1700

Data Index: 4403894 (Open Web Text)

Max Activating Token Index: 200

Text #10

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0545. Min Act: -0.1700

Data Index: 3282765 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0641. Min Act: -0.1700

Data Index: 1410982 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0560. Min Act: -0.1700

Data Index: 8824698 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0565. Min Act: -0.1700

Data Index: 429931 (Open Web Text)

Max Activating Token Index: 914

Text #14

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0420. Min Act: -0.1700

Data Index: 4053545 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0552. Min Act: -0.1700

Data Index: 7137722 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0337. Min Act: -0.1700

Data Index: 8356046 (Open Web Text)

Max Activating Token Index: 877

Text #17

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0416. Min Act: -0.1700

Data Index: 8770496 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0311. Min Act: -0.1700

Data Index: 7513300 (Open Web Text)

Max Activating Token Index: 91

Text #19

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0131. Min Act: -0.1700

Data Index: 5554847 (Open Web Text)

Max Activating Token Index: 206