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

Dataset: Open Web Text

Neuron 995 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: 3.7529. Min Range: -3.7529

Max Act: 3.7529. Min Act: -0.1700

Data Index: 5896745 (Open Web Text)

Max Activating Token Index: 573

Text #1

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6812. Min Act: -0.1700

Data Index: 5474378 (Open Web Text)

Max Activating Token Index: 370

Text #2

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6908. Min Act: -0.1700

Data Index: 8308097 (Open Web Text)

Max Activating Token Index: 378

Text #3

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6834. Min Act: -0.1700

Data Index: 50940 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6655. Min Act: -0.1700

Data Index: 8382402 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6487. Min Act: -0.1700

Data Index: 909767 (Open Web Text)

Max Activating Token Index: 818

Text #6

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6470. Min Act: -0.1700

Data Index: 8332737 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6493. Min Act: -0.1700

Data Index: 2489445 (Open Web Text)

Max Activating Token Index: 820

Text #8

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6078. Min Act: -0.1700

Data Index: 6723056 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6234. Min Act: -0.1700

Data Index: 3657401 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6150. Min Act: -0.1700

Data Index: 524193 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.6186. Min Act: -0.1700

Data Index: 4221528 (Open Web Text)

Max Activating Token Index: 358

Text #12

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5980. Min Act: -0.1700

Data Index: 2905841 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5915. Min Act: -0.1700

Data Index: 5025272 (Open Web Text)

Max Activating Token Index: 148

Text #14

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5798. Min Act: -0.1700

Data Index: 8045061 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5771. Min Act: -0.1700

Data Index: 4187355 (Open Web Text)

Max Activating Token Index: 465

Text #16

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5487. Min Act: -0.1700

Data Index: 7996236 (Open Web Text)

Max Activating Token Index: 374

Text #17

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5376. Min Act: -0.1700

Data Index: 3619856 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5340. Min Act: -0.1700

Data Index: 7788326 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 3.7529. Min Range: -3.7529

Max Act: 3.5201. Min Act: -0.1700

Data Index: 614856 (Open Web Text)

Max Activating Token Index: 165