Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 8257770 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 2416219 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.2698. Min Act: -0.1700
Data Index: 5500423 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.2698. Min Act: -0.1700
Data Index: 7147637 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.1760. Min Act: -0.1700
Data Index: 7613234 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.1135. Min Act: -0.1700
Data Index: 8257771 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.0823. Min Act: -0.1700
Data Index: 2933177 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.0823. Min Act: -0.1700
Data Index: 5737726 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.0510. Min Act: -0.1700
Data Index: 2815990 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.0510. Min Act: -0.1700
Data Index: 7766699 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.0198. Min Act: -0.1700
Data Index: 6848590 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.0510. Min Act: -0.1700
Data Index: 2573678 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4260. Min Range: -7.4260
Max Act: 7.0198. Min Act: -0.1700
Data Index: 3462546 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4260. Min Range: -7.4260
Max Act: 6.9885. Min Act: -0.1700
Data Index: 2441550 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4260. Min Range: -7.4260
Max Act: 6.9260. Min Act: -0.1700
Data Index: 3565563 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4260. Min Range: -7.4260
Max Act: 6.9260. Min Act: -0.1700
Data Index: 974120 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4260. Min Range: -7.4260
Max Act: 6.8948. Min Act: -0.1700
Data Index: 6238321 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4260. Min Range: -7.4260
Max Act: 6.8323. Min Act: -0.1700
Data Index: 2016801 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4260. Min Range: -7.4260
Max Act: 6.8010. Min Act: -0.1700
Data Index: 2412998 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4260. Min Range: -7.4260
Max Act: 6.7698. Min Act: -0.1700
Data Index: 2067794 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19