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

Dataset: Open Web Text

Neuron 1738 in Layer 5

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: 6.0130. Min Range: -6.0130

Max Act: 6.0130. Min Act: -0.1700

Data Index: 8311415 (Open Web Text)

Max Activating Token Index: 1019

Text #1

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.9107. Min Act: -0.1700

Data Index: 5504388 (Open Web Text)

Max Activating Token Index: 983

Text #2

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.8374. Min Act: -0.1700

Data Index: 2458129 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.7973. Min Act: -0.1700

Data Index: 2175432 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.7401. Min Act: -0.1700

Data Index: 6073544 (Open Web Text)

Max Activating Token Index: 35

Text #5

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.7545. Min Act: -0.1700

Data Index: 7619613 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.7233. Min Act: -0.1700

Data Index: 8105420 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.7058. Min Act: -0.1700

Data Index: 1696352 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6925. Min Act: -0.1700

Data Index: 7341645 (Open Web Text)

Max Activating Token Index: 484

Text #9

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6514. Min Act: -0.1700

Data Index: 4586626 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6718. Min Act: -0.1700

Data Index: 216300 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6063. Min Act: -0.1700

Data Index: 8774782 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6490. Min Act: -0.1700

Data Index: 2087061 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6248. Min Act: -0.1700

Data Index: 6874097 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6861. Min Act: -0.1700

Data Index: 8762028 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6171. Min Act: -0.1700

Data Index: 1443541 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6147. Min Act: -0.1700

Data Index: 4810405 (Open Web Text)

Max Activating Token Index: 1018

Text #17

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6078. Min Act: -0.1700

Data Index: 1922844 (Open Web Text)

Max Activating Token Index: 884

Text #18

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6188. Min Act: -0.1700

Data Index: 2190335 (Open Web Text)

Max Activating Token Index: 910

Text #19

Max Range: 6.0130. Min Range: -6.0130

Max Act: 5.6234. Min Act: -0.1700

Data Index: 7503618 (Open Web Text)

Max Activating Token Index: 726