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

Dataset: Open Web Text

Neuron 782 in Layer 2

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: 4.7280. Min Range: -4.7280

Max Act: 4.7280. Min Act: -0.1700

Data Index: 5982257 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.7062. Min Act: -0.1700

Data Index: 2128579 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.6844. Min Act: -0.1700

Data Index: 5340106 (Open Web Text)

Max Activating Token Index: 636

Text #3

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.6298. Min Act: -0.1700

Data Index: 127007 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5749. Min Act: -0.1700

Data Index: 4718402 (Open Web Text)

Max Activating Token Index: 781

Text #5

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.6281. Min Act: -0.1700

Data Index: 1187127 (Open Web Text)

Max Activating Token Index: 367

Text #6

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5809. Min Act: -0.1700

Data Index: 1836651 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.6020. Min Act: -0.1700

Data Index: 8663744 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5879. Min Act: -0.1700

Data Index: 6463622 (Open Web Text)

Max Activating Token Index: 642

Text #9

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5454. Min Act: -0.1700

Data Index: 1231570 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5594. Min Act: -0.1700

Data Index: 5097512 (Open Web Text)

Max Activating Token Index: 361

Text #11

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5632. Min Act: -0.1700

Data Index: 8094914 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5467. Min Act: -0.1700

Data Index: 2676991 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5117. Min Act: -0.1700

Data Index: 4423140 (Open Web Text)

Max Activating Token Index: 685

Text #14

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5581. Min Act: -0.1700

Data Index: 6324647 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5465. Min Act: -0.1700

Data Index: 5313523 (Open Web Text)

Max Activating Token Index: 732

Text #16

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5312. Min Act: -0.1700

Data Index: 4399487 (Open Web Text)

Max Activating Token Index: 561

Text #17

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5228. Min Act: -0.1700

Data Index: 2830196 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5039. Min Act: -0.1700

Data Index: 3212622 (Open Web Text)

Max Activating Token Index: 571

Text #19

Max Range: 4.7280. Min Range: -4.7280

Max Act: 4.5051. Min Act: -0.1700

Data Index: 4426570 (Open Web Text)

Max Activating Token Index: 921