Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5903 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2282. Min Range: -7.2282
Max Act: 7.2282. Min Act: -0.1700
Data Index: 5081783 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2282. Min Range: -7.2282
Max Act: 7.1969. Min Act: -0.1700
Data Index: 4482983 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2282. Min Range: -7.2282
Max Act: 7.1657. Min Act: -0.1700
Data Index: 1639810 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2282. Min Range: -7.2282
Max Act: 7.1657. Min Act: -0.1700
Data Index: 4594341 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2282. Min Range: -7.2282
Max Act: 7.0407. Min Act: -0.1700
Data Index: 1510003 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2282. Min Range: -7.2282
Max Act: 7.0407. Min Act: -0.1700
Data Index: 4686235 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.9469. Min Act: -0.1700
Data Index: 3505089 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.8532. Min Act: -0.1700
Data Index: 733131 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.8532. Min Act: -0.1700
Data Index: 879037 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.8219. Min Act: -0.1700
Data Index: 6909501 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.8532. Min Act: -0.1700
Data Index: 8664071 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.8219. Min Act: -0.1700
Data Index: 646219 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.7907. Min Act: -0.1700
Data Index: 4458748 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.7594. Min Act: -0.1700
Data Index: 2162757 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.6344. Min Act: -0.1700
Data Index: 5820686 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.6032. Min Act: -0.1700
Data Index: 792785 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.6032. Min Act: -0.1700
Data Index: 331439 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.6032. Min Act: -0.1700
Data Index: 6661563 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.5407. Min Act: -0.1700
Data Index: 4709757 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2282. Min Range: -7.2282
Max Act: 6.5719. Min Act: -0.1700
Data Index: 4874498 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19