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

Dataset: Open Web Text

Neuron 1813 in Layer 3

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: 2.3649. Min Range: -2.3649

Max Act: 2.3623. Min Act: -0.1700

Data Index: 5397517 (Open Web Text)

Max Activating Token Index: 799

Text #1

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3649. Min Act: -0.1700

Data Index: 4329118 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3571. Min Act: -0.1700

Data Index: 4419568 (Open Web Text)

Max Activating Token Index: 478

Text #3

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3478. Min Act: -0.1700

Data Index: 3537343 (Open Web Text)

Max Activating Token Index: 909

Text #4

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3625. Min Act: -0.1700

Data Index: 187426 (Open Web Text)

Max Activating Token Index: 371

Text #5

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3509. Min Act: -0.1700

Data Index: 4238109 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3298. Min Act: -0.1700

Data Index: 2322670 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3483. Min Act: -0.1700

Data Index: 745389 (Open Web Text)

Max Activating Token Index: 574

Text #8

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3452. Min Act: -0.1700

Data Index: 5403164 (Open Web Text)

Max Activating Token Index: 315

Text #9

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3110. Min Act: -0.1700

Data Index: 844172 (Open Web Text)

Max Activating Token Index: 342

Text #10

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3184. Min Act: -0.1700

Data Index: 8340900 (Open Web Text)

Max Activating Token Index: 379

Text #11

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3211. Min Act: -0.1700

Data Index: 8349872 (Open Web Text)

Max Activating Token Index: 930

Text #12

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3171. Min Act: -0.1700

Data Index: 5752953 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.2989. Min Act: -0.1700

Data Index: 4955479 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.3051. Min Act: -0.1700

Data Index: 1404099 (Open Web Text)

Max Activating Token Index: 162

Text #15

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.2977. Min Act: -0.1700

Data Index: 8746397 (Open Web Text)

Max Activating Token Index: 359

Text #16

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.2995. Min Act: -0.1700

Data Index: 3309934 (Open Web Text)

Max Activating Token Index: 650

Text #17

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.2679. Min Act: -0.1700

Data Index: 3599658 (Open Web Text)

Max Activating Token Index: 379

Text #18

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.2737. Min Act: -0.1700

Data Index: 6540615 (Open Web Text)

Max Activating Token Index: 267

Text #19

Max Range: 2.3649. Min Range: -2.3649

Max Act: 2.2863. Min Act: -0.1700

Data Index: 7081993 (Open Web Text)

Max Activating Token Index: 393