Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2264 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.9417. Min Act: -0.1700
Data Index: 3741715 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.6605. Min Act: -0.1700
Data Index: 4551245 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.5042. Min Act: -0.1700
Data Index: 8060400 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.4417. Min Act: -0.1700
Data Index: 146124 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.4105. Min Act: -0.1700
Data Index: 4923412 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.4105. Min Act: -0.1700
Data Index: 3579767 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.4105. Min Act: -0.1700
Data Index: 323367 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.4417. Min Act: -0.1700
Data Index: 1497202 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.3792. Min Act: -0.1700
Data Index: 8446248 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.3480. Min Act: -0.1700
Data Index: 2591149 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.3480. Min Act: -0.1700
Data Index: 1789767 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.3480. Min Act: -0.1700
Data Index: 5754717 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2542. Min Act: -0.1700
Data Index: 5518237 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2855. Min Act: -0.1700
Data Index: 5958636 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2230. Min Act: -0.1700
Data Index: 5211623 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2542. Min Act: -0.1700
Data Index: 715086 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2542. Min Act: -0.1700
Data Index: 5683457 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2542. Min Act: -0.1700
Data Index: 7028453 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2542. Min Act: -0.1700
Data Index: 6937795 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9417. Min Range: -7.9417
Max Act: 7.2230. Min Act: -0.1700
Data Index: 6312044 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19