Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.9282. Min Act: -0.1700
Data Index: 4281319 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.8657. Min Act: -0.1700
Data Index: 7549339 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.7719. Min Act: -0.1700
Data Index: 4313785 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.7719. Min Act: -0.1700
Data Index: 8062153 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.7094. Min Act: -0.1700
Data Index: 4281314 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.7094. Min Act: -0.1700
Data Index: 4771053 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.7094. Min Act: -0.1700
Data Index: 4281317 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.7094. Min Act: -0.1700
Data Index: 7843723 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.6782. Min Act: -0.1700
Data Index: 8058877 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.6782. Min Act: -0.1700
Data Index: 4281315 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.6782. Min Act: -0.1700
Data Index: 8094567 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.6782. Min Act: -0.1700
Data Index: 3060399 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.6469. Min Act: -0.1700
Data Index: 7820063 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.6469. Min Act: -0.1700
Data Index: 3718180 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.5532. Min Act: -0.1700
Data Index: 4281313 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.5844. Min Act: -0.1700
Data Index: 957854 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.5532. Min Act: -0.1700
Data Index: 6201158 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.5844. Min Act: -0.1700
Data Index: 5265881 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.4594. Min Act: -0.1700
Data Index: 7591641 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9282. Min Range: -5.9282
Max Act: 5.4594. Min Act: -0.1700
Data Index: 1961080 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19