Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6300. Min Range: -9.6300
Max Act: 9.6300. Min Act: -0.1700
Data Index: 3392038 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6300. Min Range: -9.6300
Max Act: 9.4425. Min Act: -0.1700
Data Index: 5853725 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6300. Min Range: -9.6300
Max Act: 9.3175. Min Act: -0.1700
Data Index: 5529867 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6300. Min Range: -9.6300
Max Act: 9.3175. Min Act: -0.1700
Data Index: 3378355 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6300. Min Range: -9.6300
Max Act: 9.0675. Min Act: -0.1700
Data Index: 5645350 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6300. Min Range: -9.6300
Max Act: 9.1300. Min Act: -0.1700
Data Index: 5942855 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.9425. Min Act: -0.1700
Data Index: 5529868 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.8175. Min Act: -0.1700
Data Index: 5853726 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.8175. Min Act: -0.1700
Data Index: 3392039 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.6925. Min Act: -0.1700
Data Index: 3378353 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.6300. Min Act: -0.1700
Data Index: 4298021 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.6925. Min Act: -0.1700
Data Index: 4298020 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.6925. Min Act: -0.1700
Data Index: 5736280 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.6300. Min Act: -0.1700
Data Index: 5529869 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.6300. Min Act: -0.1700
Data Index: 310478 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.5050. Min Act: -0.1700
Data Index: 5983171 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.5050. Min Act: -0.1700
Data Index: 3378354 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.5675. Min Act: -0.1700
Data Index: 5551136 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.4425. Min Act: -0.1700
Data Index: 1788913 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6300. Min Range: -9.6300
Max Act: 8.4425. Min Act: -0.1700
Data Index: 295114 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19