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

Dataset: Open Web Text

Neuron 558 in Layer 5

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: 4.1816. Min Range: -4.1816

Max Act: 4.1816. Min Act: -0.1700

Data Index: 173591 (Open Web Text)

Max Activating Token Index: 774

Text #1

Max Range: 4.1816. Min Range: -4.1816

Max Act: 4.0843. Min Act: -0.1700

Data Index: 4746933 (Open Web Text)

Max Activating Token Index: 631

Text #2

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.9076. Min Act: -0.1700

Data Index: 7985640 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.8917. Min Act: -0.1700

Data Index: 8352131 (Open Web Text)

Max Activating Token Index: 871

Text #4

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.8376. Min Act: -0.1700

Data Index: 6735710 (Open Web Text)

Max Activating Token Index: 831

Text #5

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.8194. Min Act: -0.1700

Data Index: 7579916 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.8230. Min Act: -0.1700

Data Index: 8098078 (Open Web Text)

Max Activating Token Index: 344

Text #7

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.8186. Min Act: -0.1700

Data Index: 3035505 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7649. Min Act: -0.1700

Data Index: 3568627 (Open Web Text)

Max Activating Token Index: 548

Text #9

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7819. Min Act: -0.1700

Data Index: 5675959 (Open Web Text)

Max Activating Token Index: 469

Text #10

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.8014. Min Act: -0.1700

Data Index: 8587164 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7761. Min Act: -0.1700

Data Index: 2741495 (Open Web Text)

Max Activating Token Index: 956

Text #12

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7663. Min Act: -0.1700

Data Index: 1232454 (Open Web Text)

Max Activating Token Index: 876

Text #13

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7714. Min Act: -0.1700

Data Index: 4496561 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7648. Min Act: -0.1700

Data Index: 8440717 (Open Web Text)

Max Activating Token Index: 504

Text #15

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7546. Min Act: -0.1700

Data Index: 6309058 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7633. Min Act: -0.1700

Data Index: 1963273 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7483. Min Act: -0.1700

Data Index: 5984897 (Open Web Text)

Max Activating Token Index: 221

Text #18

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7514. Min Act: -0.1700

Data Index: 1091629 (Open Web Text)

Max Activating Token Index: 901

Text #19

Max Range: 4.1816. Min Range: -4.1816

Max Act: 3.7170. Min Act: -0.1700

Data Index: 3081191 (Open Web Text)

Max Activating Token Index: 979