Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0840. Min Range: -7.0840
Max Act: 7.0840. Min Act: -0.1700
Data Index: 4611629 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.8965. Min Act: -0.1700
Data Index: 8450171 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.8965. Min Act: -0.1700
Data Index: 4097627 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.8653. Min Act: -0.1700
Data Index: 2904713 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.8028. Min Act: -0.1700
Data Index: 1147474 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.8028. Min Act: -0.1700
Data Index: 5913147 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.7403. Min Act: -0.1700
Data Index: 6798355 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.6465. Min Act: -0.1700
Data Index: 4266527 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.6465. Min Act: -0.1700
Data Index: 1028475 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.6153. Min Act: -0.1700
Data Index: 6283936 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.6465. Min Act: -0.1700
Data Index: 5842368 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.6153. Min Act: -0.1700
Data Index: 5219513 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.5840. Min Act: -0.1700
Data Index: 8692759 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.5528. Min Act: -0.1700
Data Index: 4097618 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.5528. Min Act: -0.1700
Data Index: 8265137 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.5528. Min Act: -0.1700
Data Index: 7235501 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.5215. Min Act: -0.1700
Data Index: 5834780 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.5215. Min Act: -0.1700
Data Index: 5590807 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.4903. Min Act: -0.1700
Data Index: 6775654 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0840. Min Range: -7.0840
Max Act: 6.4590. Min Act: -0.1700
Data Index: 7668879 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19