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

Dataset: Open Web Text

Neuron 978 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: 1.7121. Min Range: -1.7121

Max Act: 1.7121. Min Act: -0.0590

Data Index: 2246874 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6950. Min Act: -0.0590

Data Index: 1724774 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6737. Min Act: -0.1559

Data Index: 6170531 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6675. Min Act: -0.0590

Data Index: 1649322 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6578. Min Act: -0.0951

Data Index: 4738724 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6603. Min Act: -0.1041

Data Index: 7383933 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6540. Min Act: -0.0590

Data Index: 2748772 (Open Web Text)

Max Activating Token Index: 997

Text #7

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6510. Min Act: -0.0773

Data Index: 4524155 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6564. Min Act: -0.0590

Data Index: 260360 (Open Web Text)

Max Activating Token Index: 989

Text #9

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6493. Min Act: -0.0745

Data Index: 7895927 (Open Web Text)

Max Activating Token Index: 975

Text #10

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6326. Min Act: -0.0590

Data Index: 6744766 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6403. Min Act: -0.0590

Data Index: 8761421 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6374. Min Act: -0.0590

Data Index: 8736172 (Open Web Text)

Max Activating Token Index: 1013

Text #13

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6370. Min Act: -0.0777

Data Index: 5051308 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6309. Min Act: -0.1178

Data Index: 1263263 (Open Web Text)

Max Activating Token Index: 991

Text #15

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6263. Min Act: -0.0590

Data Index: 6962268 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6291. Min Act: -0.1098

Data Index: 8637626 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6284. Min Act: -0.0998

Data Index: 2866513 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6235. Min Act: -0.0590

Data Index: 3091317 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.6200. Min Act: -0.1201

Data Index: 2252584 (Open Web Text)

Max Activating Token Index: 1023