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

Dataset: Open Web Text

Neuron 2087 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: 3.2342. Min Range: -3.2342

Max Act: 3.2342. Min Act: -0.1700

Data Index: 8228032 (Open Web Text)

Max Activating Token Index: 790

Text #1

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1909. Min Act: -0.1700

Data Index: 7056346 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1608. Min Act: -0.1700

Data Index: 2721859 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1547. Min Act: -0.1700

Data Index: 6765342 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1465. Min Act: -0.1700

Data Index: 8617327 (Open Web Text)

Max Activating Token Index: 811

Text #5

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1768. Min Act: -0.1700

Data Index: 3834908 (Open Web Text)

Max Activating Token Index: 840

Text #6

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1450. Min Act: -0.1700

Data Index: 5855008 (Open Web Text)

Max Activating Token Index: 214

Text #7

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1016. Min Act: -0.1700

Data Index: 992030 (Open Web Text)

Max Activating Token Index: 942

Text #8

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1190. Min Act: -0.1700

Data Index: 415446 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1345. Min Act: -0.1700

Data Index: 272798 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1218. Min Act: -0.1700

Data Index: 6385489 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.0896. Min Act: -0.1700

Data Index: 4560960 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.0840. Min Act: -0.1700

Data Index: 2259621 (Open Web Text)

Max Activating Token Index: 886

Text #13

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1054. Min Act: -0.1700

Data Index: 8335366 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1081. Min Act: -0.1700

Data Index: 3251182 (Open Web Text)

Max Activating Token Index: 397

Text #15

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1059. Min Act: -0.1700

Data Index: 902455 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.1197. Min Act: -0.1700

Data Index: 8568103 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.0549. Min Act: -0.1700

Data Index: 2721858 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.0794. Min Act: -0.1700

Data Index: 8104369 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 3.2342. Min Range: -3.2342

Max Act: 3.0648. Min Act: -0.1700

Data Index: 4502322 (Open Web Text)

Max Activating Token Index: 491