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

Dataset: Open Web Text

Neuron 2962 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: 2.8356. Min Range: -2.8356

Max Act: 2.8356. Min Act: -0.1700

Data Index: 3676475 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.7116. Min Act: -0.1700

Data Index: 1190708 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.7059. Min Act: -0.1700

Data Index: 8622359 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.7244. Min Act: -0.1700

Data Index: 588208 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6695. Min Act: -0.1700

Data Index: 3326256 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6802. Min Act: -0.1700

Data Index: 2256270 (Open Web Text)

Max Activating Token Index: 554

Text #6

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6848. Min Act: -0.1700

Data Index: 1898974 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6931. Min Act: -0.1700

Data Index: 2612289 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6465. Min Act: -0.1700

Data Index: 650621 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6771. Min Act: -0.1700

Data Index: 6851940 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6630. Min Act: -0.1700

Data Index: 5287371 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6582. Min Act: -0.1700

Data Index: 1640572 (Open Web Text)

Max Activating Token Index: 999

Text #12

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6025. Min Act: -0.1700

Data Index: 6514236 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6474. Min Act: -0.1700

Data Index: 7766252 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.5979. Min Act: -0.1700

Data Index: 4293500 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.5826. Min Act: -0.1700

Data Index: 6406976 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.5633. Min Act: -0.1700

Data Index: 7304387 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.5919. Min Act: -0.1700

Data Index: 6118237 (Open Web Text)

Max Activating Token Index: 1002

Text #18

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.6187. Min Act: -0.1700

Data Index: 4097523 (Open Web Text)

Max Activating Token Index: 746

Text #19

Max Range: 2.8356. Min Range: -2.8356

Max Act: 2.5982. Min Act: -0.1700

Data Index: 3225942 (Open Web Text)

Max Activating Token Index: 552