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

Dataset: Open Web Text

Neuron 2369 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: 1.7547. Min Range: -1.7547

Max Act: 1.7547. Min Act: -0.1700

Data Index: 1489822 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6839. Min Act: -0.1699

Data Index: 6956697 (Open Web Text)

Max Activating Token Index: 656

Text #2

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6681. Min Act: -0.1700

Data Index: 2722954 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6614. Min Act: -0.1700

Data Index: 5720126 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6352. Min Act: -0.1700

Data Index: 246313 (Open Web Text)

Max Activating Token Index: 59

Text #5

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6415. Min Act: -0.1700

Data Index: 1381952 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6277. Min Act: -0.1700

Data Index: 7278539 (Open Web Text)

Max Activating Token Index: 711

Text #7

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6297. Min Act: -0.1700

Data Index: 1850189 (Open Web Text)

Max Activating Token Index: 754

Text #8

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6238. Min Act: -0.1695

Data Index: 557000 (Open Web Text)

Max Activating Token Index: 866

Text #9

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6305. Min Act: -0.1700

Data Index: 7262146 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6210. Min Act: -0.1700

Data Index: 5209041 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6128. Min Act: -0.1700

Data Index: 4340537 (Open Web Text)

Max Activating Token Index: 814

Text #12

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6132. Min Act: -0.1700

Data Index: 2427126 (Open Web Text)

Max Activating Token Index: 231

Text #13

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6001. Min Act: -0.1700

Data Index: 1931124 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.5993. Min Act: -0.1700

Data Index: 2302748 (Open Web Text)

Max Activating Token Index: 615

Text #15

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6122. Min Act: -0.1700

Data Index: 6212600 (Open Web Text)

Max Activating Token Index: 811

Text #16

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.5893. Min Act: -0.1700

Data Index: 1960493 (Open Web Text)

Max Activating Token Index: 201

Text #17

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6090. Min Act: -0.1700

Data Index: 3593636 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.6025. Min Act: -0.1700

Data Index: 7542057 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.5996. Min Act: -0.1700

Data Index: 7685555 (Open Web Text)

Max Activating Token Index: 651