Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2097 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.2798. Min Act: -0.1700
Data Index: 7700860 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.2169. Min Act: -0.1700
Data Index: 8129522 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1855. Min Act: -0.1700
Data Index: 4677045 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1540. Min Act: -0.1700
Data Index: 3130025 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1382. Min Act: -0.1700
Data Index: 1181404 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1382. Min Act: -0.1700
Data Index: 8571702 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1382. Min Act: -0.1700
Data Index: 6043965 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1382. Min Act: -0.1700
Data Index: 4562860 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1225. Min Act: -0.1700
Data Index: 6368380 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1225. Min Act: -0.1700
Data Index: 937585 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.0910. Min Act: -0.1700
Data Index: 6141438 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1067. Min Act: -0.1700
Data Index: 2700941 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1067. Min Act: -0.1700
Data Index: 1355952 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.0910. Min Act: -0.1700
Data Index: 7186724 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.0752. Min Act: -0.1700
Data Index: 6267344 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.1067. Min Act: -0.1700
Data Index: 5527753 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.0752. Min Act: -0.1700
Data Index: 8392134 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.0752. Min Act: -0.1700
Data Index: 6074513 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.0752. Min Act: -0.1700
Data Index: 602528 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2798. Min Range: -3.2798
Max Act: 3.0437. Min Act: -0.1700
Data Index: 8393934 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19