Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4016 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2029. Min Range: -6.2029
Max Act: 6.2029. Min Act: -0.1700
Data Index: 6079941 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2029. Min Range: -6.2029
Max Act: 6.1404. Min Act: -0.1700
Data Index: 3846338 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.8904. Min Act: -0.1700
Data Index: 614784 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.8904. Min Act: -0.1700
Data Index: 2386273 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.8904. Min Act: -0.1700
Data Index: 5324615 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.9217. Min Act: -0.1700
Data Index: 3277105 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.8592. Min Act: -0.1700
Data Index: 4660916 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7967. Min Act: -0.1700
Data Index: 6551872 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7967. Min Act: -0.1700
Data Index: 4281332 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7654. Min Act: -0.1700
Data Index: 2637814 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7654. Min Act: -0.1700
Data Index: 7893367 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7654. Min Act: -0.1700
Data Index: 2355213 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7342. Min Act: -0.1700
Data Index: 2544647 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7342. Min Act: -0.1700
Data Index: 838632 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7342. Min Act: -0.1700
Data Index: 4672633 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7342. Min Act: -0.1700
Data Index: 3949646 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7029. Min Act: -0.1700
Data Index: 1287165 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.7029. Min Act: -0.1700
Data Index: 3240890 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.6404. Min Act: -0.1700
Data Index: 4064638 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2029. Min Range: -6.2029
Max Act: 5.6717. Min Act: -0.1700
Data Index: 2525352 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19