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

Dataset: Open Web Text

Neuron 2125 in Layer 2

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: 1.8637. Min Range: -1.8637

Max Act: 1.8637. Min Act: -0.1700

Data Index: 8721952 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.8210. Min Act: -0.1700

Data Index: 5238856 (Open Web Text)

Max Activating Token Index: 803

Text #2

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.8115. Min Act: -0.1700

Data Index: 128180 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.8016. Min Act: -0.1700

Data Index: 953921 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7978. Min Act: -0.1700

Data Index: 2080784 (Open Web Text)

Max Activating Token Index: 180

Text #5

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7904. Min Act: -0.1700

Data Index: 5687416 (Open Web Text)

Max Activating Token Index: 119

Text #6

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7810. Min Act: -0.1700

Data Index: 4918722 (Open Web Text)

Max Activating Token Index: 297

Text #7

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.8020. Min Act: -0.1700

Data Index: 8430230 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7837. Min Act: -0.1700

Data Index: 8807196 (Open Web Text)

Max Activating Token Index: 862

Text #9

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7625. Min Act: -0.1700

Data Index: 8290736 (Open Web Text)

Max Activating Token Index: 45

Text #10

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7669. Min Act: -0.1700

Data Index: 6743890 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7641. Min Act: -0.1700

Data Index: 5976597 (Open Web Text)

Max Activating Token Index: 605

Text #12

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7560. Min Act: -0.1700

Data Index: 630787 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7358. Min Act: -0.1700

Data Index: 8642358 (Open Web Text)

Max Activating Token Index: 955

Text #14

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7536. Min Act: -0.1700

Data Index: 6514412 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7557. Min Act: -0.1700

Data Index: 4730520 (Open Web Text)

Max Activating Token Index: 922

Text #16

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7432. Min Act: -0.1700

Data Index: 4846564 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7534. Min Act: -0.1700

Data Index: 4878385 (Open Web Text)

Max Activating Token Index: 542

Text #18

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7394. Min Act: -0.1700

Data Index: 2850620 (Open Web Text)

Max Activating Token Index: 26

Text #19

Max Range: 1.8637. Min Range: -1.8637

Max Act: 1.7428. Min Act: -0.1700

Data Index: 4922740 (Open Web Text)

Max Activating Token Index: 438