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

Dataset: Open Web Text

Neuron 2499 in Layer 4

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: 3.6086. Min Range: -3.6086

Max Act: 3.5875. Min Act: -0.1700

Data Index: 5326861 (Open Web Text)

Max Activating Token Index: 520

Text #1

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.6086. Min Act: -0.1700

Data Index: 6734877 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5844. Min Act: -0.1700

Data Index: 7633697 (Open Web Text)

Max Activating Token Index: 963

Text #3

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5554. Min Act: -0.1700

Data Index: 5536819 (Open Web Text)

Max Activating Token Index: 724

Text #4

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5775. Min Act: -0.1700

Data Index: 5391238 (Open Web Text)

Max Activating Token Index: 810

Text #5

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5543. Min Act: -0.1700

Data Index: 6183012 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5677. Min Act: -0.1700

Data Index: 297555 (Open Web Text)

Max Activating Token Index: 962

Text #7

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5451. Min Act: -0.1700

Data Index: 7145912 (Open Web Text)

Max Activating Token Index: 349

Text #8

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.5027. Min Act: -0.1700

Data Index: 3165406 (Open Web Text)

Max Activating Token Index: 825

Text #9

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4968. Min Act: -0.1700

Data Index: 5723182 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4802. Min Act: -0.1700

Data Index: 7633646 (Open Web Text)

Max Activating Token Index: 911

Text #11

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4752. Min Act: -0.1700

Data Index: 8157579 (Open Web Text)

Max Activating Token Index: 740

Text #12

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4730. Min Act: -0.1700

Data Index: 7367585 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4893. Min Act: -0.1700

Data Index: 5460942 (Open Web Text)

Max Activating Token Index: 940

Text #14

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4590. Min Act: -0.1700

Data Index: 7382365 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4599. Min Act: -0.1700

Data Index: 69143 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4915. Min Act: -0.1700

Data Index: 79169 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4558. Min Act: -0.1700

Data Index: 2189933 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4873. Min Act: -0.1700

Data Index: 4853266 (Open Web Text)

Max Activating Token Index: 689

Text #19

Max Range: 3.6086. Min Range: -3.6086

Max Act: 3.4699. Min Act: -0.1700

Data Index: 1246014 (Open Web Text)

Max Activating Token Index: 414