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

Dataset: Open Web Text

Neuron 1499 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: 4.3750. Min Range: -4.3750

Max Act: 4.3750. Min Act: -0.1700

Data Index: 1448856 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.2626. Min Act: -0.1700

Data Index: 2132875 (Open Web Text)

Max Activating Token Index: 419

Text #2

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.2080. Min Act: -0.1700

Data Index: 374812 (Open Web Text)

Max Activating Token Index: 595

Text #3

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.1288. Min Act: -0.1700

Data Index: 1300359 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.1564. Min Act: -0.1700

Data Index: 2956563 (Open Web Text)

Max Activating Token Index: 746

Text #5

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.1391. Min Act: -0.1700

Data Index: 3614050 (Open Web Text)

Max Activating Token Index: 308

Text #6

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.1296. Min Act: -0.1700

Data Index: 5975351 (Open Web Text)

Max Activating Token Index: 882

Text #7

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0798. Min Act: -0.1700

Data Index: 6887621 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.1147. Min Act: -0.1700

Data Index: 4281115 (Open Web Text)

Max Activating Token Index: 90

Text #9

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.1073. Min Act: -0.1700

Data Index: 4050057 (Open Web Text)

Max Activating Token Index: 138

Text #10

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0978. Min Act: -0.1700

Data Index: 1218800 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0726. Min Act: -0.1700

Data Index: 3331814 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0576. Min Act: -0.1700

Data Index: 4970963 (Open Web Text)

Max Activating Token Index: 202

Text #13

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0954. Min Act: -0.1700

Data Index: 6307903 (Open Web Text)

Max Activating Token Index: 109

Text #14

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0494. Min Act: -0.1700

Data Index: 3250322 (Open Web Text)

Max Activating Token Index: 714

Text #15

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0517. Min Act: -0.1700

Data Index: 8264850 (Open Web Text)

Max Activating Token Index: 182

Text #16

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0573. Min Act: -0.1700

Data Index: 4009720 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0879. Min Act: -0.1700

Data Index: 6363941 (Open Web Text)

Max Activating Token Index: 89

Text #18

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0208. Min Act: -0.1700

Data Index: 5685709 (Open Web Text)

Max Activating Token Index: 795

Text #19

Max Range: 4.3750. Min Range: -4.3750

Max Act: 4.0392. Min Act: -0.1700

Data Index: 4719446 (Open Web Text)

Max Activating Token Index: 687