Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5403 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2375. Min Range: -6.2375
Max Act: 6.2375. Min Act: -0.1700
Data Index: 6932114 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2375. Min Range: -6.2375
Max Act: 6.0188. Min Act: -0.1700
Data Index: 1110805 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.9250. Min Act: -0.1700
Data Index: 6476393 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.8938. Min Act: -0.1700
Data Index: 975723 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.8625. Min Act: -0.1700
Data Index: 2872668 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.8625. Min Act: -0.1700
Data Index: 7106944 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7101376 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.8313. Min Act: -0.1700
Data Index: 1862277 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.8000. Min Act: -0.1700
Data Index: 7192059 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7688. Min Act: -0.1700
Data Index: 6498905 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7688. Min Act: -0.1700
Data Index: 1479252 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7375. Min Act: -0.1700
Data Index: 4463099 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7375. Min Act: -0.1700
Data Index: 1909772 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7688. Min Act: -0.1700
Data Index: 5721363 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7375. Min Act: -0.1700
Data Index: 6518794 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7063. Min Act: -0.1700
Data Index: 6528009 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7063. Min Act: -0.1700
Data Index: 8089398 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7063. Min Act: -0.1700
Data Index: 6908119 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7063. Min Act: -0.1700
Data Index: 2917317 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2375. Min Range: -6.2375
Max Act: 5.7063. Min Act: -0.1700
Data Index: 614714 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19