Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5865 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2126. Min Range: -6.2126
Max Act: 6.2126. Min Act: -0.1700
Data Index: 5775535 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2126. Min Range: -6.2126
Max Act: 6.0876. Min Act: -0.1700
Data Index: 3892647 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.8689. Min Act: -0.1700
Data Index: 1304156 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.7751. Min Act: -0.1700
Data Index: 5205576 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.7439. Min Act: -0.1700
Data Index: 1168334 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.7126. Min Act: -0.1700
Data Index: 8800201 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.7126. Min Act: -0.1700
Data Index: 7070699 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.7126. Min Act: -0.1700
Data Index: 4585029 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.7126. Min Act: -0.1700
Data Index: 3075478 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6814. Min Act: -0.1700
Data Index: 4282021 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6814. Min Act: -0.1700
Data Index: 8800199 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6814. Min Act: -0.1700
Data Index: 9645 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6814. Min Act: -0.1700
Data Index: 6872649 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6501. Min Act: -0.1700
Data Index: 2605522 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6501. Min Act: -0.1700
Data Index: 6657199 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6501. Min Act: -0.1700
Data Index: 6835575 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6501. Min Act: -0.1700
Data Index: 2686324 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6501. Min Act: -0.1700
Data Index: 8662763 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6189. Min Act: -0.1700
Data Index: 7383657 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2126. Min Range: -6.2126
Max Act: 5.6189. Min Act: -0.1700
Data Index: 7383658 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19