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

Dataset: Open Web Text

Neuron 1909 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: 1.5778. Min Range: -1.5778

Max Act: 1.5778. Min Act: -0.1700

Data Index: 2052026 (Open Web Text)

Max Activating Token Index: 377

Text #1

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5750. Min Act: -0.1698

Data Index: 2052023 (Open Web Text)

Max Activating Token Index: 573

Text #2

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5668. Min Act: -0.1700

Data Index: 2769966 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5726. Min Act: -0.1700

Data Index: 5378787 (Open Web Text)

Max Activating Token Index: 828

Text #4

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5639. Min Act: -0.1700

Data Index: 735371 (Open Web Text)

Max Activating Token Index: 245

Text #5

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5396. Min Act: -0.1695

Data Index: 2951664 (Open Web Text)

Max Activating Token Index: 874

Text #6

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5429. Min Act: -0.1700

Data Index: 4732882 (Open Web Text)

Max Activating Token Index: 141

Text #7

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5391. Min Act: -0.1693

Data Index: 996404 (Open Web Text)

Max Activating Token Index: 311

Text #8

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5421. Min Act: -0.1700

Data Index: 1891495 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5249. Min Act: -0.1666

Data Index: 4732886 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5345. Min Act: -0.1700

Data Index: 3368633 (Open Web Text)

Max Activating Token Index: 806

Text #11

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5212. Min Act: -0.1700

Data Index: 2052031 (Open Web Text)

Max Activating Token Index: 76

Text #12

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5312. Min Act: -0.1700

Data Index: 4442036 (Open Web Text)

Max Activating Token Index: 977

Text #13

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5084. Min Act: -0.1700

Data Index: 4487154 (Open Web Text)

Max Activating Token Index: 906

Text #14

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5130. Min Act: -0.1693

Data Index: 4496729 (Open Web Text)

Max Activating Token Index: 152

Text #15

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5142. Min Act: -0.1699

Data Index: 8600479 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5093. Min Act: -0.1699

Data Index: 5426544 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.4865. Min Act: -0.1696

Data Index: 3481812 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.4993. Min Act: -0.1699

Data Index: 3070912 (Open Web Text)

Max Activating Token Index: 154

Text #19

Max Range: 1.5778. Min Range: -1.5778

Max Act: 1.5085. Min Act: -0.1698

Data Index: 5309087 (Open Web Text)

Max Activating Token Index: 440