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

Dataset: Open Web Text

Neuron 2148 in Layer 2

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: 1.6714. Min Range: -1.6714

Max Act: 1.6714. Min Act: -0.1700

Data Index: 1825404 (Open Web Text)

Max Activating Token Index: 840

Text #1

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6535. Min Act: -0.1700

Data Index: 6317805 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6614. Min Act: -0.1700

Data Index: 1490824 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6574. Min Act: -0.1700

Data Index: 7432912 (Open Web Text)

Max Activating Token Index: 885

Text #4

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6447. Min Act: -0.1700

Data Index: 7680331 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6437. Min Act: -0.1700

Data Index: 5214399 (Open Web Text)

Max Activating Token Index: 976

Text #6

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6334. Min Act: -0.1700

Data Index: 3361926 (Open Web Text)

Max Activating Token Index: 937

Text #7

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6439. Min Act: -0.1700

Data Index: 5439275 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6371. Min Act: -0.1700

Data Index: 7821005 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6269. Min Act: -0.1700

Data Index: 7778230 (Open Web Text)

Max Activating Token Index: 979

Text #10

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6128. Min Act: -0.1700

Data Index: 2637054 (Open Web Text)

Max Activating Token Index: 371

Text #11

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6015. Min Act: -0.1700

Data Index: 347133 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6216. Min Act: -0.1700

Data Index: 4090563 (Open Web Text)

Max Activating Token Index: 1003

Text #13

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6222. Min Act: -0.1700

Data Index: 4319235 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6299. Min Act: -0.1700

Data Index: 6543639 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6319. Min Act: -0.1700

Data Index: 2791267 (Open Web Text)

Max Activating Token Index: 1016

Text #16

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6218. Min Act: -0.1700

Data Index: 5854952 (Open Web Text)

Max Activating Token Index: 625

Text #17

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6160. Min Act: -0.1700

Data Index: 2001697 (Open Web Text)

Max Activating Token Index: 878

Text #18

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6103. Min Act: -0.1700

Data Index: 1357087 (Open Web Text)

Max Activating Token Index: 713

Text #19

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.5982. Min Act: -0.1700

Data Index: 1180017 (Open Web Text)

Max Activating Token Index: 960