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

Dataset: Open Web Text

Neuron 2589 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: 3.6310. Min Range: -3.6310

Max Act: 3.6287. Min Act: -0.1700

Data Index: 2589329 (Open Web Text)

Max Activating Token Index: 930

Text #1

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.6310. Min Act: -0.1700

Data Index: 3006376 (Open Web Text)

Max Activating Token Index: 563

Text #2

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.6081. Min Act: -0.1700

Data Index: 667426 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5719. Min Act: -0.1700

Data Index: 6770033 (Open Web Text)

Max Activating Token Index: 639

Text #4

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5934. Min Act: -0.1700

Data Index: 2172042 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5761. Min Act: -0.1700

Data Index: 6755240 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5665. Min Act: -0.1700

Data Index: 6090169 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5597. Min Act: -0.1700

Data Index: 6437550 (Open Web Text)

Max Activating Token Index: 804

Text #8

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5393. Min Act: -0.1700

Data Index: 5343354 (Open Web Text)

Max Activating Token Index: 535

Text #9

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5220. Min Act: -0.1700

Data Index: 2662879 (Open Web Text)

Max Activating Token Index: 478

Text #10

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5303. Min Act: -0.1700

Data Index: 1603577 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4960. Min Act: -0.1700

Data Index: 6051214 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4995. Min Act: -0.1700

Data Index: 1252383 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5106. Min Act: -0.1700

Data Index: 6233438 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.5190. Min Act: -0.1700

Data Index: 4103852 (Open Web Text)

Max Activating Token Index: 628

Text #15

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4886. Min Act: -0.1700

Data Index: 2593441 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4653. Min Act: -0.1700

Data Index: 5260231 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4816. Min Act: -0.1700

Data Index: 1697344 (Open Web Text)

Max Activating Token Index: 787

Text #18

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4838. Min Act: -0.1700

Data Index: 1812945 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 3.6310. Min Range: -3.6310

Max Act: 3.4897. Min Act: -0.1700

Data Index: 5978305 (Open Web Text)

Max Activating Token Index: 275