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

Dataset: Open Web Text

Neuron 2363 in Layer 6

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: 3.8258. Min Range: -3.8258

Max Act: 3.8151. Min Act: -0.1700

Data Index: 8313640 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.8258. Min Act: -0.1700

Data Index: 7931183 (Open Web Text)

Max Activating Token Index: 936

Text #2

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.7236. Min Act: -0.1700

Data Index: 1172529 (Open Web Text)

Max Activating Token Index: 416

Text #3

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6826. Min Act: -0.1700

Data Index: 6428907 (Open Web Text)

Max Activating Token Index: 98

Text #4

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.7179. Min Act: -0.1700

Data Index: 8198083 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.7142. Min Act: -0.1700

Data Index: 7336733 (Open Web Text)

Max Activating Token Index: 1007

Text #6

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6716. Min Act: -0.1700

Data Index: 2221462 (Open Web Text)

Max Activating Token Index: 962

Text #7

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6473. Min Act: -0.1700

Data Index: 7481668 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6234. Min Act: -0.1700

Data Index: 1786608 (Open Web Text)

Max Activating Token Index: 750

Text #9

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6767. Min Act: -0.1700

Data Index: 1425811 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6842. Min Act: -0.1700

Data Index: 7454510 (Open Web Text)

Max Activating Token Index: 739

Text #11

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6502. Min Act: -0.1700

Data Index: 2725446 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6316. Min Act: -0.1700

Data Index: 7832246 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6517. Min Act: -0.1700

Data Index: 4338597 (Open Web Text)

Max Activating Token Index: 467

Text #14

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6052. Min Act: -0.1700

Data Index: 4672608 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6194. Min Act: -0.1700

Data Index: 2275956 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.5858. Min Act: -0.1700

Data Index: 2018177 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.5779. Min Act: -0.1700

Data Index: 5993347 (Open Web Text)

Max Activating Token Index: 750

Text #18

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.6062. Min Act: -0.1700

Data Index: 6530783 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 3.8258. Min Range: -3.8258

Max Act: 3.5946. Min Act: -0.1700

Data Index: 5457846 (Open Web Text)

Max Activating Token Index: 807