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

Dataset: Open Web Text

Neuron 1294 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: 5.3828. Min Range: -5.3828

Max Act: 5.3828. Min Act: -0.1700

Data Index: 5165002 (Open Web Text)

Max Activating Token Index: 915

Text #1

Max Range: 5.3828. Min Range: -5.3828

Max Act: 5.0484. Min Act: -0.1700

Data Index: 822467 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 5.3828. Min Range: -5.3828

Max Act: 5.0333. Min Act: -0.1700

Data Index: 6447653 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 5.3828. Min Range: -5.3828

Max Act: 5.0393. Min Act: -0.1700

Data Index: 5901009 (Open Web Text)

Max Activating Token Index: 857

Text #4

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.9830. Min Act: -0.1700

Data Index: 8316708 (Open Web Text)

Max Activating Token Index: 544

Text #5

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.9883. Min Act: -0.1700

Data Index: 2147784 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.9881. Min Act: -0.1700

Data Index: 3926036 (Open Web Text)

Max Activating Token Index: 577

Text #7

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.9847. Min Act: -0.1700

Data Index: 6635937 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.9419. Min Act: -0.1700

Data Index: 4675157 (Open Web Text)

Max Activating Token Index: 603

Text #9

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.9219. Min Act: -0.1700

Data Index: 3859738 (Open Web Text)

Max Activating Token Index: 402

Text #10

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8999. Min Act: -0.1700

Data Index: 1179178 (Open Web Text)

Max Activating Token Index: 419

Text #11

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8744. Min Act: -0.1700

Data Index: 4342947 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8559. Min Act: -0.1700

Data Index: 7902315 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8470. Min Act: -0.1700

Data Index: 5966847 (Open Web Text)

Max Activating Token Index: 216

Text #14

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8119. Min Act: -0.1700

Data Index: 4916733 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8415. Min Act: -0.1700

Data Index: 2162464 (Open Web Text)

Max Activating Token Index: 993

Text #16

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8411. Min Act: -0.1700

Data Index: 2731996 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.7976. Min Act: -0.1700

Data Index: 4488643 (Open Web Text)

Max Activating Token Index: 864

Text #18

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.8122. Min Act: -0.1700

Data Index: 4593136 (Open Web Text)

Max Activating Token Index: 515

Text #19

Max Range: 5.3828. Min Range: -5.3828

Max Act: 4.7956. Min Act: -0.1700

Data Index: 2308723 (Open Web Text)

Max Activating Token Index: 257