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

Dataset: Open Web Text

Neuron 1799 in Layer 1

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: 1.6826. Min Range: -1.6826

Max Act: 1.6794. Min Act: -0.1700

Data Index: 4799470 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6826. Min Act: -0.1700

Data Index: 3892460 (Open Web Text)

Max Activating Token Index: 166

Text #2

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6710. Min Act: -0.1689

Data Index: 8608942 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6763. Min Act: -0.1700

Data Index: 717924 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6338. Min Act: -0.1700

Data Index: 7741354 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6330. Min Act: -0.1698

Data Index: 8413193 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6184. Min Act: -0.1700

Data Index: 6216569 (Open Web Text)

Max Activating Token Index: 206

Text #7

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.6083. Min Act: -0.1688

Data Index: 4547366 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5886. Min Act: -0.1700

Data Index: 3195293 (Open Web Text)

Max Activating Token Index: 323

Text #9

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5867. Min Act: -0.1700

Data Index: 5577789 (Open Web Text)

Max Activating Token Index: 112

Text #10

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5803. Min Act: -0.1700

Data Index: 5961218 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5822. Min Act: -0.1700

Data Index: 8409322 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5850. Min Act: -0.1700

Data Index: 1887856 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5764. Min Act: -0.1700

Data Index: 756884 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5718. Min Act: -0.1700

Data Index: 4912784 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5709. Min Act: -0.1696

Data Index: 3497927 (Open Web Text)

Max Activating Token Index: 525

Text #16

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5761. Min Act: -0.1699

Data Index: 8329770 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5570. Min Act: -0.1700

Data Index: 7896440 (Open Web Text)

Max Activating Token Index: 180

Text #18

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5629. Min Act: -0.1698

Data Index: 4940418 (Open Web Text)

Max Activating Token Index: 480

Text #19

Max Range: 1.6826. Min Range: -1.6826

Max Act: 1.5638. Min Act: -0.1700

Data Index: 461144 (Open Web Text)

Max Activating Token Index: 198