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

Dataset: Open Web Text

Neuron 2779 in Layer 3

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: 3.8241. Min Range: -3.8241

Max Act: 3.8147. Min Act: -0.1700

Data Index: 3419357 (Open Web Text)

Max Activating Token Index: 604

Text #1

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.8241. Min Act: -0.1700

Data Index: 1265668 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.7843. Min Act: -0.1700

Data Index: 5066975 (Open Web Text)

Max Activating Token Index: 985

Text #3

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.7570. Min Act: -0.1700

Data Index: 2379894 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6812. Min Act: -0.1700

Data Index: 4437022 (Open Web Text)

Max Activating Token Index: 210

Text #5

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6850. Min Act: -0.1700

Data Index: 6027759 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6608. Min Act: -0.1700

Data Index: 4080152 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6986. Min Act: -0.1700

Data Index: 3830025 (Open Web Text)

Max Activating Token Index: 748

Text #8

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6619. Min Act: -0.1700

Data Index: 2911167 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6682. Min Act: -0.1700

Data Index: 8486069 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6616. Min Act: -0.1700

Data Index: 4323877 (Open Web Text)

Max Activating Token Index: 1015

Text #11

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6565. Min Act: -0.1700

Data Index: 5308958 (Open Web Text)

Max Activating Token Index: 999

Text #12

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.6278. Min Act: -0.1700

Data Index: 2265859 (Open Web Text)

Max Activating Token Index: 883

Text #13

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.5828. Min Act: -0.1700

Data Index: 8765906 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.5870. Min Act: -0.1700

Data Index: 4097333 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.5597. Min Act: -0.1700

Data Index: 8140967 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.5939. Min Act: -0.1700

Data Index: 2715718 (Open Web Text)

Max Activating Token Index: 1009

Text #17

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.5290. Min Act: -0.1700

Data Index: 2047164 (Open Web Text)

Max Activating Token Index: 452

Text #18

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.5164. Min Act: -0.1700

Data Index: 3193010 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 3.8241. Min Range: -3.8241

Max Act: 3.5239. Min Act: -0.1700

Data Index: 5866438 (Open Web Text)

Max Activating Token Index: 668