Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.9207. Min Act: -0.1700
Data Index: 709941 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.6395. Min Act: -0.1700
Data Index: 1093860 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.5770. Min Act: -0.1700
Data Index: 8608372 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.5457. Min Act: -0.1700
Data Index: 3518912 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.5145. Min Act: -0.1700
Data Index: 7360164 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.5145. Min Act: -0.1700
Data Index: 5902965 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.5145. Min Act: -0.1700
Data Index: 666060 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.5145. Min Act: -0.1700
Data Index: 1870973 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.4832. Min Act: -0.1700
Data Index: 4407569 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.4832. Min Act: -0.1700
Data Index: 1677033 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.4832. Min Act: -0.1700
Data Index: 5351623 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.4207. Min Act: -0.1700
Data Index: 7638838 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.4207. Min Act: -0.1700
Data Index: 7367459 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.3895. Min Act: -0.1700
Data Index: 7423225 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.3895. Min Act: -0.1700
Data Index: 1294955 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.3895. Min Act: -0.1700
Data Index: 5549391 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.3270. Min Act: -0.1700
Data Index: 861014 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.3270. Min Act: -0.1700
Data Index: 1941373 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.3270. Min Act: -0.1700
Data Index: 5814815 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9207. Min Range: -6.9207
Max Act: 6.3270. Min Act: -0.1700
Data Index: 3105852 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19