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

Dataset: Open Web Text

Neuron 1234 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: 0.7364. Min Range: -0.7364

Max Act: 0.7364. Min Act: -0.1700

Data Index: 6314641 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6766. Min Act: -0.1700

Data Index: 1325175 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6773. Min Act: -0.1700

Data Index: 3612051 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6721. Min Act: -0.1700

Data Index: 1623561 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6496. Min Act: -0.1700

Data Index: 702694 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6413. Min Act: -0.1700

Data Index: 8653020 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6288. Min Act: -0.1700

Data Index: 5538234 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6313. Min Act: -0.1700

Data Index: 874811 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6323. Min Act: -0.1700

Data Index: 6619072 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6283. Min Act: -0.1700

Data Index: 4209892 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6274. Min Act: -0.1700

Data Index: 7089786 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6160. Min Act: -0.1700

Data Index: 7591014 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6177. Min Act: -0.1700

Data Index: 8535545 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6134. Min Act: -0.1700

Data Index: 1972254 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6121. Min Act: -0.1700

Data Index: 8331965 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6058. Min Act: -0.1700

Data Index: 5317725 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6005. Min Act: -0.1700

Data Index: 3011060 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6108. Min Act: -0.1700

Data Index: 755184 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.6065. Min Act: -0.1700

Data Index: 3515559 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 0.7364. Min Range: -0.7364

Max Act: 0.5915. Min Act: -0.1700

Data Index: 5475949 (Open Web Text)

Max Activating Token Index: 1023