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

Dataset: Open Web Text

Neuron 1179 in Layer 1

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: 1.8800. Min Range: -1.8800

Max Act: 1.8800. Min Act: -0.1700

Data Index: 4541141 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.7886. Min Act: -0.1700

Data Index: 5040919 (Open Web Text)

Max Activating Token Index: 804

Text #2

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.7427. Min Act: -0.1700

Data Index: 449224 (Open Web Text)

Max Activating Token Index: 988

Text #3

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.7240. Min Act: -0.1700

Data Index: 1792905 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.7211. Min Act: -0.1700

Data Index: 2994485 (Open Web Text)

Max Activating Token Index: 793

Text #5

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.7131. Min Act: -0.1699

Data Index: 3241349 (Open Web Text)

Max Activating Token Index: 980

Text #6

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6984. Min Act: -0.1700

Data Index: 435362 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6762. Min Act: -0.1699

Data Index: 1060310 (Open Web Text)

Max Activating Token Index: 266

Text #8

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6928. Min Act: -0.1700

Data Index: 174311 (Open Web Text)

Max Activating Token Index: 997

Text #9

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6702. Min Act: -0.1699

Data Index: 1818575 (Open Web Text)

Max Activating Token Index: 783

Text #10

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6833. Min Act: -0.1700

Data Index: 5155213 (Open Web Text)

Max Activating Token Index: 919

Text #11

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6831. Min Act: -0.1700

Data Index: 5459137 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6829. Min Act: -0.1700

Data Index: 220196 (Open Web Text)

Max Activating Token Index: 465

Text #13

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6765. Min Act: -0.1700

Data Index: 1221044 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6723. Min Act: -0.1700

Data Index: 6832283 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6658. Min Act: -0.1700

Data Index: 2312351 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6626. Min Act: -0.1700

Data Index: 841200 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6600. Min Act: -0.1699

Data Index: 2603669 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6641. Min Act: -0.1699

Data Index: 4809822 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.6604. Min Act: -0.1699

Data Index: 435377 (Open Web Text)

Max Activating Token Index: 129