Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.7374. Min Act: -0.1700
Data Index: 1074695 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.6436. Min Act: -0.1700
Data Index: 3861835 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.5499. Min Act: -0.1700
Data Index: 2749927 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.5499. Min Act: -0.1700
Data Index: 923582 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.5499. Min Act: -0.1700
Data Index: 3852113 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.5499. Min Act: -0.1700
Data Index: 8096024 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.3311. Min Act: -0.1700
Data Index: 722988 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.2999. Min Act: -0.1700
Data Index: 6036027 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.2686. Min Act: -0.1700
Data Index: 331396 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.2686. Min Act: -0.1700
Data Index: 2977286 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.2374. Min Act: -0.1700
Data Index: 2220019 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.2374. Min Act: -0.1700
Data Index: 1689239 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.2686. Min Act: -0.1700
Data Index: 564921 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.2686. Min Act: -0.1700
Data Index: 3492162 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.1749. Min Act: -0.1700
Data Index: 1834072 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.1436. Min Act: -0.1700
Data Index: 4387900 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.1749. Min Act: -0.1700
Data Index: 1515319 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.1436. Min Act: -0.1700
Data Index: 691397 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.1436. Min Act: -0.1700
Data Index: 2978417 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7374. Min Range: -6.7374
Max Act: 6.1436. Min Act: -0.1700
Data Index: 7788873 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19