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

Dataset: Open Web Text

Neuron 1648 in Layer 3

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: 3.8682. Min Range: -3.8682

Max Act: 3.8682. Min Act: -0.1700

Data Index: 2856609 (Open Web Text)

Max Activating Token Index: 744

Text #1

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.7853. Min Act: -0.1700

Data Index: 3425191 (Open Web Text)

Max Activating Token Index: 573

Text #2

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.8152. Min Act: -0.1700

Data Index: 501381 (Open Web Text)

Max Activating Token Index: 622

Text #3

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.7541. Min Act: -0.1700

Data Index: 3342919 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.7468. Min Act: -0.1700

Data Index: 6916886 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.7207. Min Act: -0.1700

Data Index: 2627242 (Open Web Text)

Max Activating Token Index: 638

Text #6

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.6267. Min Act: -0.1700

Data Index: 1931757 (Open Web Text)

Max Activating Token Index: 974

Text #7

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.6010. Min Act: -0.1700

Data Index: 1265605 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.5590. Min Act: -0.1700

Data Index: 3854665 (Open Web Text)

Max Activating Token Index: 541

Text #9

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.5437. Min Act: -0.1700

Data Index: 4858959 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.5372. Min Act: -0.1700

Data Index: 827902 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.5448. Min Act: -0.1700

Data Index: 8293236 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.5048. Min Act: -0.1700

Data Index: 4119831 (Open Web Text)

Max Activating Token Index: 448

Text #13

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.5258. Min Act: -0.1700

Data Index: 7040421 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.5181. Min Act: -0.1700

Data Index: 4732563 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.4609. Min Act: -0.1700

Data Index: 1579421 (Open Web Text)

Max Activating Token Index: 799

Text #16

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.4694. Min Act: -0.1700

Data Index: 4234288 (Open Web Text)

Max Activating Token Index: 725

Text #17

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.4699. Min Act: -0.1700

Data Index: 5880988 (Open Web Text)

Max Activating Token Index: 884

Text #18

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.4578. Min Act: -0.1700

Data Index: 5779710 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 3.8682. Min Range: -3.8682

Max Act: 3.4682. Min Act: -0.1700

Data Index: 677073 (Open Web Text)

Max Activating Token Index: 631