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

Dataset: Open Web Text

Neuron 709 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: 3.5731. Min Range: -3.5731

Max Act: 3.5731. Min Act: -0.1700

Data Index: 1341664 (Open Web Text)

Max Activating Token Index: 308

Text #1

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4823. Min Act: -0.1700

Data Index: 4187290 (Open Web Text)

Max Activating Token Index: 736

Text #2

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4577. Min Act: -0.1700

Data Index: 213809 (Open Web Text)

Max Activating Token Index: 989

Text #3

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4563. Min Act: -0.1700

Data Index: 2081349 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4538. Min Act: -0.1700

Data Index: 7691638 (Open Web Text)

Max Activating Token Index: 608

Text #5

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4289. Min Act: -0.1700

Data Index: 7981394 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4145. Min Act: -0.1700

Data Index: 2547705 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.3876. Min Act: -0.1700

Data Index: 5961142 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4313. Min Act: -0.1700

Data Index: 524071 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4028. Min Act: -0.1700

Data Index: 7974428 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4053. Min Act: -0.1700

Data Index: 1124280 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4284. Min Act: -0.1700

Data Index: 1344304 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4072. Min Act: -0.1700

Data Index: 6564324 (Open Web Text)

Max Activating Token Index: 283

Text #13

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.3565. Min Act: -0.1700

Data Index: 4180722 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.3741. Min Act: -0.1700

Data Index: 2519697 (Open Web Text)

Max Activating Token Index: 214

Text #15

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4071. Min Act: -0.1700

Data Index: 5090779 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.3900. Min Act: -0.1700

Data Index: 3219187 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.3919. Min Act: -0.1700

Data Index: 8643031 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.3543. Min Act: -0.1700

Data Index: 6552630 (Open Web Text)

Max Activating Token Index: 614

Text #19

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.3726. Min Act: -0.1700

Data Index: 5312289 (Open Web Text)

Max Activating Token Index: 399