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

Dataset: Open Web Text

Neuron 2177 in Layer 6

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: 4.8894. Min Range: -4.8894

Max Act: 4.8894. Min Act: -0.1700

Data Index: 31637 (Open Web Text)

Max Activating Token Index: 163

Text #1

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.6960. Min Act: -0.1700

Data Index: 656592 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.6512. Min Act: -0.1700

Data Index: 8290454 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.6510. Min Act: -0.1700

Data Index: 5266131 (Open Web Text)

Max Activating Token Index: 334

Text #4

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.5849. Min Act: -0.1700

Data Index: 7531582 (Open Web Text)

Max Activating Token Index: 288

Text #5

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.5672. Min Act: -0.1700

Data Index: 8351622 (Open Web Text)

Max Activating Token Index: 290

Text #6

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.6238. Min Act: -0.1700

Data Index: 1678145 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.5588. Min Act: -0.1700

Data Index: 62785 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.5196. Min Act: -0.1700

Data Index: 5130226 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.5317. Min Act: -0.1700

Data Index: 7442446 (Open Web Text)

Max Activating Token Index: 790

Text #10

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.5065. Min Act: -0.1700

Data Index: 2684390 (Open Web Text)

Max Activating Token Index: 839

Text #11

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.4467. Min Act: -0.1700

Data Index: 2864706 (Open Web Text)

Max Activating Token Index: 607

Text #12

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.4254. Min Act: -0.1700

Data Index: 7199483 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.4543. Min Act: -0.1700

Data Index: 2042353 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.4430. Min Act: -0.1700

Data Index: 5352623 (Open Web Text)

Max Activating Token Index: 635

Text #15

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.4296. Min Act: -0.1700

Data Index: 6118 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.4299. Min Act: -0.1700

Data Index: 7784774 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.4005. Min Act: -0.1700

Data Index: 7205104 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.3854. Min Act: -0.1700

Data Index: 1117590 (Open Web Text)

Max Activating Token Index: 396

Text #19

Max Range: 4.8894. Min Range: -4.8894

Max Act: 4.3918. Min Act: -0.1700

Data Index: 4592463 (Open Web Text)

Max Activating Token Index: 557