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

Dataset: Open Web Text

Neuron 2852 in Layer 0

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: 11.0824. Min Range: -11.0824

Max Act: 11.0824. Min Act: -0.1700

Data Index: 4908094 (Open Web Text)

Max Activating Token Index: 936

Text #1

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.8396. Min Act: -0.1700

Data Index: 2671686 (Open Web Text)

Max Activating Token Index: 918

Text #2

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.7777. Min Act: -0.1700

Data Index: 1652875 (Open Web Text)

Max Activating Token Index: 904

Text #3

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.7054. Min Act: -0.1700

Data Index: 561081 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.4805. Min Act: -0.1700

Data Index: 8014791 (Open Web Text)

Max Activating Token Index: 912

Text #5

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.4703. Min Act: -0.1700

Data Index: 881363 (Open Web Text)

Max Activating Token Index: 922

Text #6

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.3805. Min Act: -0.1700

Data Index: 6599635 (Open Web Text)

Max Activating Token Index: 892

Text #7

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.2258. Min Act: -0.1700

Data Index: 7138285 (Open Web Text)

Max Activating Token Index: 371

Text #8

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.2405. Min Act: -0.1700

Data Index: 6711543 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.3643. Min Act: -0.1700

Data Index: 167207 (Open Web Text)

Max Activating Token Index: 942

Text #10

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.3179. Min Act: -0.1700

Data Index: 5016102 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.1960. Min Act: -0.1700

Data Index: 2133542 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.2918. Min Act: -0.1700

Data Index: 5110370 (Open Web Text)

Max Activating Token Index: 934

Text #13

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.1812. Min Act: -0.1700

Data Index: 1589826 (Open Web Text)

Max Activating Token Index: 938

Text #14

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.1916. Min Act: -0.1700

Data Index: 8718131 (Open Web Text)

Max Activating Token Index: 914

Text #15

Max Range: 11.0824. Min Range: -11.0824

Max Act: 9.9724. Min Act: -0.1700

Data Index: 2826830 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.0975. Min Act: -0.1700

Data Index: 3283585 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.0976. Min Act: -0.1700

Data Index: 3579070 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 11.0824. Min Range: -11.0824

Max Act: 10.0999. Min Act: -0.1700

Data Index: 3359874 (Open Web Text)

Max Activating Token Index: 875

Text #19

Max Range: 11.0824. Min Range: -11.0824

Max Act: 9.9497. Min Act: -0.1700

Data Index: 1146704 (Open Web Text)

Max Activating Token Index: 934