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

Dataset: Open Web Text

Neuron 49 in Layer 0

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: 1.5345. Min Range: -1.5345

Max Act: 1.5345. Min Act: -0.1388

Data Index: 6646841 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.5186. Min Act: -0.1441

Data Index: 1755790 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.5063. Min Act: -0.0882

Data Index: 3238767 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.5119. Min Act: -0.1447

Data Index: 362604 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4959. Min Act: -0.1240

Data Index: 6054246 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.5018. Min Act: -0.0993

Data Index: 443854 (Open Web Text)

Max Activating Token Index: 865

Text #6

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4902. Min Act: -0.1647

Data Index: 5259124 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4846. Min Act: -0.1168

Data Index: 6586799 (Open Web Text)

Max Activating Token Index: 827

Text #8

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4900. Min Act: -0.0857

Data Index: 7207069 (Open Web Text)

Max Activating Token Index: 931

Text #9

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4980. Min Act: -0.1271

Data Index: 2485964 (Open Web Text)

Max Activating Token Index: 875

Text #10

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4888. Min Act: -0.1255

Data Index: 1685204 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4813. Min Act: -0.1224

Data Index: 5561305 (Open Web Text)

Max Activating Token Index: 819

Text #12

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4786. Min Act: -0.1445

Data Index: 7865335 (Open Web Text)

Max Activating Token Index: 607

Text #13

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4793. Min Act: -0.1612

Data Index: 5082250 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4830. Min Act: -0.1142

Data Index: 8060701 (Open Web Text)

Max Activating Token Index: 818

Text #15

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4838. Min Act: -0.1483

Data Index: 2448850 (Open Web Text)

Max Activating Token Index: 405

Text #16

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4742. Min Act: -0.1651

Data Index: 5605290 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4748. Min Act: -0.1398

Data Index: 199567 (Open Web Text)

Max Activating Token Index: 402

Text #18

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4763. Min Act: -0.1600

Data Index: 8082497 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4724. Min Act: -0.1551

Data Index: 2046167 (Open Web Text)

Max Activating Token Index: 689