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

Dataset: Open Web Text

Neuron 2558 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: 3.4766. Min Range: -3.4766

Max Act: 3.4766. Min Act: -0.1700

Data Index: 8572196 (Open Web Text)

Max Activating Token Index: 510

Text #1

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.4035. Min Act: -0.1700

Data Index: 6727328 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3534. Min Act: -0.1700

Data Index: 7271450 (Open Web Text)

Max Activating Token Index: 925

Text #3

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3339. Min Act: -0.1700

Data Index: 6501928 (Open Web Text)

Max Activating Token Index: 864

Text #4

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3339. Min Act: -0.1700

Data Index: 7118931 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3227. Min Act: -0.1700

Data Index: 4847776 (Open Web Text)

Max Activating Token Index: 670

Text #6

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.3018. Min Act: -0.1700

Data Index: 1042484 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2833. Min Act: -0.1700

Data Index: 1109665 (Open Web Text)

Max Activating Token Index: 587

Text #8

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2826. Min Act: -0.1700

Data Index: 7769989 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2889. Min Act: -0.1700

Data Index: 4896492 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2575. Min Act: -0.1700

Data Index: 4538393 (Open Web Text)

Max Activating Token Index: 378

Text #11

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2990. Min Act: -0.1700

Data Index: 2171471 (Open Web Text)

Max Activating Token Index: 778

Text #12

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2644. Min Act: -0.1700

Data Index: 4570543 (Open Web Text)

Max Activating Token Index: 506

Text #13

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2673. Min Act: -0.1700

Data Index: 4965504 (Open Web Text)

Max Activating Token Index: 758

Text #14

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2614. Min Act: -0.1700

Data Index: 6797856 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2724. Min Act: -0.1700

Data Index: 1382462 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2394. Min Act: -0.1700

Data Index: 5617613 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2482. Min Act: -0.1700

Data Index: 8720253 (Open Web Text)

Max Activating Token Index: 863

Text #18

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2495. Min Act: -0.1700

Data Index: 1632810 (Open Web Text)

Max Activating Token Index: 174

Text #19

Max Range: 3.4766. Min Range: -3.4766

Max Act: 3.2201. Min Act: -0.1700

Data Index: 2110254 (Open Web Text)

Max Activating Token Index: 538