Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4105. Min Range: -6.4105
Max Act: 6.4105. Min Act: -0.1700
Data Index: 2229614 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4105. Min Range: -6.4105
Max Act: 6.4105. Min Act: -0.1700
Data Index: 999306 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4105. Min Range: -6.4105
Max Act: 6.1605. Min Act: -0.1700
Data Index: 3532918 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4105. Min Range: -6.4105
Max Act: 6.0355. Min Act: -0.1700
Data Index: 4387133 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.9105. Min Act: -0.1700
Data Index: 1492012 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.9105. Min Act: -0.1700
Data Index: 3620879 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.9105. Min Act: -0.1700
Data Index: 8545906 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.9105. Min Act: -0.1700
Data Index: 2760867 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.8167. Min Act: -0.1700
Data Index: 8266672 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.8480. Min Act: -0.1700
Data Index: 3487754 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.8480. Min Act: -0.1700
Data Index: 778465 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.8167. Min Act: -0.1700
Data Index: 3652956 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.7855. Min Act: -0.1700
Data Index: 4237837 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.7855. Min Act: -0.1700
Data Index: 5693551 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.7542. Min Act: -0.1700
Data Index: 1614546 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 7392552 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 2001619 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 7133454 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.6917. Min Act: -0.1700
Data Index: 1744095 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4105. Min Range: -6.4105
Max Act: 5.6917. Min Act: -0.1700
Data Index: 6597352 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19