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

Dataset: Open Web Text

Neuron 671 in Layer 4

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: 3.7700. Min Range: -3.7700

Max Act: 3.5803. Min Act: -0.1700

Data Index: 3479305 (Open Web Text)

Max Activating Token Index: 490

Text #1

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5967. Min Act: -0.1700

Data Index: 8396142 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.7700. Min Act: -0.1699

Data Index: 7874563 (Open Web Text)

Max Activating Token Index: 269

Text #3

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6253. Min Act: -0.1700

Data Index: 6578855 (Open Web Text)

Max Activating Token Index: 795

Text #4

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6596. Min Act: -0.1700

Data Index: 7643850 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6578. Min Act: -0.1700

Data Index: 6079671 (Open Web Text)

Max Activating Token Index: 452

Text #6

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.7200. Min Act: -0.1699

Data Index: 5918309 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.4798. Min Act: -0.1700

Data Index: 1846941 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6214. Min Act: -0.1700

Data Index: 1427340 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6216. Min Act: -0.1700

Data Index: 5913152 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6087. Min Act: -0.1700

Data Index: 7361422 (Open Web Text)

Max Activating Token Index: 146

Text #11

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.4278. Min Act: -0.1700

Data Index: 6907418 (Open Web Text)

Max Activating Token Index: 300

Text #12

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6161. Min Act: -0.1700

Data Index: 2104555 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5343. Min Act: -0.1700

Data Index: 805922 (Open Web Text)

Max Activating Token Index: 420

Text #14

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5906. Min Act: -0.1700

Data Index: 5245602 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6366. Min Act: -0.1700

Data Index: 2736118 (Open Web Text)

Max Activating Token Index: 127

Text #16

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5607. Min Act: -0.1699

Data Index: 3211475 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5456. Min Act: -0.1700

Data Index: 1415721 (Open Web Text)

Max Activating Token Index: 261

Text #18

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.4504. Min Act: -0.1700

Data Index: 7389742 (Open Web Text)

Max Activating Token Index: 750

Text #19

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6273. Min Act: -0.1700

Data Index: 1050588 (Open Web Text)

Max Activating Token Index: 788