Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2755 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.9947. Min Range: -14.9947
Max Act: 14.9947. Min Act: -0.1700
Data Index: 6009405 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.9947. Min Act: -0.1700
Data Index: 4768019 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.9322. Min Act: -0.1700
Data Index: 3830572 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.8072. Min Act: -0.1700
Data Index: 3044190 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.7447. Min Act: -0.1700
Data Index: 1666102 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.7447. Min Act: -0.1700
Data Index: 8273622 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.7447. Min Act: -0.1700
Data Index: 2236537 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.6822. Min Act: -0.1700
Data Index: 1709754 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.6822. Min Act: -0.1700
Data Index: 5769546 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.6822. Min Act: -0.1700
Data Index: 5962719 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.6822. Min Act: -0.1700
Data Index: 3268903 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.5572. Min Act: -0.1700
Data Index: 2096526 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.6197. Min Act: -0.1700
Data Index: 5769542 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.5572. Min Act: -0.1700
Data Index: 6227194 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.5572. Min Act: -0.1700
Data Index: 722241 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.5572. Min Act: -0.1700
Data Index: 1832098 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.4947. Min Act: -0.1700
Data Index: 3550616 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.4947. Min Act: -0.1700
Data Index: 5125867 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.5572. Min Act: -0.1700
Data Index: 5126848 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.9947. Min Range: -14.9947
Max Act: 13.4322. Min Act: -0.1700
Data Index: 3789749 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19