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

Dataset: Open Web Text

Neuron 568 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: 3.2929. Min Range: -3.2929

Max Act: 3.2929. Min Act: -0.1700

Data Index: 6682217 (Open Web Text)

Max Activating Token Index: 873

Text #1

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.2005. Min Act: -0.1700

Data Index: 8226696 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.2169. Min Act: -0.1700

Data Index: 4664184 (Open Web Text)

Max Activating Token Index: 566

Text #3

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1794. Min Act: -0.1700

Data Index: 6276170 (Open Web Text)

Max Activating Token Index: 783

Text #4

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.2177. Min Act: -0.1700

Data Index: 3967339 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1638. Min Act: -0.1700

Data Index: 3345870 (Open Web Text)

Max Activating Token Index: 494

Text #6

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1782. Min Act: -0.1700

Data Index: 7840222 (Open Web Text)

Max Activating Token Index: 556

Text #7

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1669. Min Act: -0.1700

Data Index: 5031915 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1532. Min Act: -0.1700

Data Index: 4726972 (Open Web Text)

Max Activating Token Index: 750

Text #9

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1060. Min Act: -0.1700

Data Index: 2359719 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1276. Min Act: -0.1700

Data Index: 2015163 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1326. Min Act: -0.1700

Data Index: 8469064 (Open Web Text)

Max Activating Token Index: 634

Text #12

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1215. Min Act: -0.1700

Data Index: 7810215 (Open Web Text)

Max Activating Token Index: 974

Text #13

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1189. Min Act: -0.1700

Data Index: 6450928 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1145. Min Act: -0.1700

Data Index: 2826770 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.0896. Min Act: -0.1700

Data Index: 7753709 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.1071. Min Act: -0.1700

Data Index: 7098575 (Open Web Text)

Max Activating Token Index: 934

Text #17

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.0967. Min Act: -0.1700

Data Index: 2797000 (Open Web Text)

Max Activating Token Index: 792

Text #18

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.0663. Min Act: -0.1700

Data Index: 6774153 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 3.2929. Min Range: -3.2929

Max Act: 3.0639. Min Act: -0.1700

Data Index: 1270276 (Open Web Text)

Max Activating Token Index: 839