Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.1584. Min Range: -8.1584
Max Act: 8.1584. Min Act: -0.1700
Data Index: 7994915 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1584. Min Range: -8.1584
Max Act: 8.0959. Min Act: -0.1700
Data Index: 1386639 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1584. Min Range: -8.1584
Max Act: 8.0334. Min Act: -0.1700
Data Index: 2054812 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1584. Min Range: -8.1584
Max Act: 8.0334. Min Act: -0.1700
Data Index: 3264207 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1584. Min Range: -8.1584
Max Act: 8.0334. Min Act: -0.1700
Data Index: 5540069 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.9397. Min Act: -0.1700
Data Index: 1166724 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.8772. Min Act: -0.1700
Data Index: 2126808 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.8459. Min Act: -0.1700
Data Index: 8454973 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.7834. Min Act: -0.1700
Data Index: 5831501 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.7834. Min Act: -0.1700
Data Index: 7642480 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.7522. Min Act: -0.1700
Data Index: 8333026 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.7209. Min Act: -0.1700
Data Index: 5936703 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.7209. Min Act: -0.1700
Data Index: 4465547 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.6897. Min Act: -0.1700
Data Index: 2039766 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.7522. Min Act: -0.1700
Data Index: 5468957 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.6584. Min Act: -0.1700
Data Index: 6840031 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.6897. Min Act: -0.1700
Data Index: 3143898 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.6584. Min Act: -0.1700
Data Index: 8735176 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.5959. Min Act: -0.1700
Data Index: 1373209 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1584. Min Range: -8.1584
Max Act: 7.5647. Min Act: -0.1700
Data Index: 2511177 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19