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

Dataset: Open Web Text

Neuron 1576 in Layer 1

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: 2.0889. Min Range: -2.0889

Max Act: 2.0889. Min Act: -0.1700

Data Index: 4548660 (Open Web Text)

Max Activating Token Index: 737

Text #1

Max Range: 2.0889. Min Range: -2.0889

Max Act: 2.0388. Min Act: -0.1700

Data Index: 4468301 (Open Web Text)

Max Activating Token Index: 991

Text #2

Max Range: 2.0889. Min Range: -2.0889

Max Act: 2.0407. Min Act: -0.1700

Data Index: 8353319 (Open Web Text)

Max Activating Token Index: 124

Text #3

Max Range: 2.0889. Min Range: -2.0889

Max Act: 2.0116. Min Act: -0.1700

Data Index: 7203079 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 2.0889. Min Range: -2.0889

Max Act: 2.0234. Min Act: -0.1689

Data Index: 8353320 (Open Web Text)

Max Activating Token Index: 855

Text #5

Max Range: 2.0889. Min Range: -2.0889

Max Act: 2.0146. Min Act: -0.1700

Data Index: 5205553 (Open Web Text)

Max Activating Token Index: 130

Text #6

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9957. Min Act: -0.1700

Data Index: 7496463 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9649. Min Act: -0.1700

Data Index: 4214603 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9571. Min Act: -0.1700

Data Index: 1802638 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9514. Min Act: -0.1700

Data Index: 1128377 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9586. Min Act: -0.1700

Data Index: 657699 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9675. Min Act: -0.1698

Data Index: 1535234 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9558. Min Act: -0.1700

Data Index: 3813272 (Open Web Text)

Max Activating Token Index: 118

Text #13

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9255. Min Act: -0.1677

Data Index: 8392763 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9332. Min Act: -0.1700

Data Index: 4927150 (Open Web Text)

Max Activating Token Index: 914

Text #15

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9317. Min Act: -0.1700

Data Index: 7588450 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9345. Min Act: -0.1700

Data Index: 8601783 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9106. Min Act: -0.1700

Data Index: 7923103 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9049. Min Act: -0.1700

Data Index: 7534482 (Open Web Text)

Max Activating Token Index: 726

Text #19

Max Range: 2.0889. Min Range: -2.0889

Max Act: 1.9033. Min Act: -0.1700

Data Index: 346280 (Open Web Text)

Max Activating Token Index: 594