Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 653 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0396. Min Range: -7.0396
Max Act: 7.0396. Min Act: -0.1700
Data Index: 1970733 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0396. Min Range: -7.0396
Max Act: 7.0396. Min Act: -0.1700
Data Index: 8753912 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0396. Min Range: -7.0396
Max Act: 7.0396. Min Act: -0.1700
Data Index: 6721607 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.9458. Min Act: -0.1700
Data Index: 8193705 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.9146. Min Act: -0.1700
Data Index: 6092246 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.9146. Min Act: -0.1700
Data Index: 8101349 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.7583. Min Act: -0.1700
Data Index: 2621252 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6958. Min Act: -0.1700
Data Index: 7427715 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.7271. Min Act: -0.1700
Data Index: 3796254 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6958. Min Act: -0.1700
Data Index: 6738565 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6646. Min Act: -0.1700
Data Index: 4858648 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6646. Min Act: -0.1700
Data Index: 7086156 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6333. Min Act: -0.1700
Data Index: 2909229 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6021. Min Act: -0.1700
Data Index: 3082518 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6021. Min Act: -0.1700
Data Index: 4239909 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.6021. Min Act: -0.1700
Data Index: 7456395 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.5083. Min Act: -0.1700
Data Index: 7112564 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.4771. Min Act: -0.1700
Data Index: 2314767 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.5396. Min Act: -0.1700
Data Index: 6622852 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0396. Min Range: -7.0396
Max Act: 6.4771. Min Act: -0.1700
Data Index: 1594548 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19