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

Dataset: Open Web Text

Neuron 1696 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: 3.5681. Min Range: -3.5681

Max Act: 3.5677. Min Act: -0.1700

Data Index: 8710682 (Open Web Text)

Max Activating Token Index: 218

Text #1

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5681. Min Act: -0.1700

Data Index: 6069715 (Open Web Text)

Max Activating Token Index: 122

Text #2

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5493. Min Act: -0.1700

Data Index: 1051422 (Open Web Text)

Max Activating Token Index: 95

Text #3

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5568. Min Act: -0.1700

Data Index: 148807 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5528. Min Act: -0.1700

Data Index: 6247202 (Open Web Text)

Max Activating Token Index: 167

Text #5

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5610. Min Act: -0.1700

Data Index: 6208842 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5227. Min Act: -0.1700

Data Index: 7847737 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5288. Min Act: -0.1700

Data Index: 8592883 (Open Web Text)

Max Activating Token Index: 798

Text #8

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5391. Min Act: -0.1700

Data Index: 5767300 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5364. Min Act: -0.1700

Data Index: 2772929 (Open Web Text)

Max Activating Token Index: 753

Text #10

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5358. Min Act: -0.1700

Data Index: 5718302 (Open Web Text)

Max Activating Token Index: 546

Text #11

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5008. Min Act: -0.1700

Data Index: 4086478 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5191. Min Act: -0.1700

Data Index: 1959255 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5045. Min Act: -0.1700

Data Index: 3268206 (Open Web Text)

Max Activating Token Index: 616

Text #14

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5101. Min Act: -0.1700

Data Index: 8693855 (Open Web Text)

Max Activating Token Index: 822

Text #15

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.4929. Min Act: -0.1700

Data Index: 4124039 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.4924. Min Act: -0.1700

Data Index: 6608433 (Open Web Text)

Max Activating Token Index: 952

Text #17

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.4852. Min Act: -0.1700

Data Index: 6893184 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.4852. Min Act: -0.1700

Data Index: 7065317 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 3.5681. Min Range: -3.5681

Max Act: 3.5052. Min Act: -0.1700

Data Index: 4276747 (Open Web Text)

Max Activating Token Index: 385