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

Dataset: Open Web Text

Neuron 608 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: 4.4714. Min Range: -4.4714

Max Act: 4.4714. Min Act: -0.1700

Data Index: 8366624 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3984. Min Act: -0.1700

Data Index: 4056481 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.4407. Min Act: -0.1700

Data Index: 4917505 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.4304. Min Act: -0.1700

Data Index: 8252110 (Open Web Text)

Max Activating Token Index: 890

Text #4

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.4210. Min Act: -0.1700

Data Index: 1296514 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3584. Min Act: -0.1700

Data Index: 7963707 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3807. Min Act: -0.1700

Data Index: 460965 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3709. Min Act: -0.1700

Data Index: 3918235 (Open Web Text)

Max Activating Token Index: 786

Text #8

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3870. Min Act: -0.1700

Data Index: 7196009 (Open Web Text)

Max Activating Token Index: 918

Text #9

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3737. Min Act: -0.1700

Data Index: 2932312 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3508. Min Act: -0.1700

Data Index: 5180742 (Open Web Text)

Max Activating Token Index: 293

Text #11

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3459. Min Act: -0.1700

Data Index: 7199751 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.2804. Min Act: -0.1700

Data Index: 5180741 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3279. Min Act: -0.1700

Data Index: 1700274 (Open Web Text)

Max Activating Token Index: 574

Text #14

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.3042. Min Act: -0.1700

Data Index: 763035 (Open Web Text)

Max Activating Token Index: 278

Text #15

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.2832. Min Act: -0.1700

Data Index: 1700280 (Open Web Text)

Max Activating Token Index: 499

Text #16

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.2949. Min Act: -0.1700

Data Index: 4394046 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.2999. Min Act: -0.1700

Data Index: 1664402 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.2893. Min Act: -0.1700

Data Index: 8278775 (Open Web Text)

Max Activating Token Index: 712

Text #19

Max Range: 4.4714. Min Range: -4.4714

Max Act: 4.2913. Min Act: -0.1700

Data Index: 5836037 (Open Web Text)

Max Activating Token Index: 177