Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.4217. Min Act: -0.1700
Data Index: 7780352 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.2342. Min Act: -0.1700
Data Index: 2106499 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.2342. Min Act: -0.1700
Data Index: 1498564 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.1405. Min Act: -0.1700
Data Index: 3465756 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.1405. Min Act: -0.1700
Data Index: 3429766 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.1092. Min Act: -0.1700
Data Index: 3950745 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.1092. Min Act: -0.1700
Data Index: 8517535 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0155. Min Act: -0.1700
Data Index: 3085683 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0467. Min Act: -0.1700
Data Index: 300691 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0155. Min Act: -0.1700
Data Index: 5793851 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0155. Min Act: -0.1700
Data Index: 7343636 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0467. Min Act: -0.1700
Data Index: 2418850 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0155. Min Act: -0.1700
Data Index: 6466108 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0155. Min Act: -0.1700
Data Index: 2210362 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4217. Min Range: -5.4217
Max Act: 4.9842. Min Act: -0.1700
Data Index: 1243044 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4217. Min Range: -5.4217
Max Act: 4.9842. Min Act: -0.1700
Data Index: 4862625 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0155. Min Act: -0.1700
Data Index: 6738653 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4217. Min Range: -5.4217
Max Act: 5.0155. Min Act: -0.1700
Data Index: 568303 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4217. Min Range: -5.4217
Max Act: 4.9842. Min Act: -0.1700
Data Index: 7352786 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4217. Min Range: -5.4217
Max Act: 4.9217. Min Act: -0.1700
Data Index: 3337812 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19