Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2992. Min Range: -6.2992
Max Act: 6.2992. Min Act: -0.1700
Data Index: 2836472 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2992. Min Range: -6.2992
Max Act: 6.1742. Min Act: -0.1700
Data Index: 997788 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2992. Min Range: -6.2992
Max Act: 6.1429. Min Act: -0.1700
Data Index: 860476 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2992. Min Range: -6.2992
Max Act: 6.0804. Min Act: -0.1700
Data Index: 6939125 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2992. Min Range: -6.2992
Max Act: 6.0492. Min Act: -0.1700
Data Index: 7325047 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2992. Min Range: -6.2992
Max Act: 6.0179. Min Act: -0.1700
Data Index: 2052662 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.9867. Min Act: -0.1700
Data Index: 4912598 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.9242. Min Act: -0.1700
Data Index: 5332263 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.9242. Min Act: -0.1700
Data Index: 5854742 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8929. Min Act: -0.1700
Data Index: 6609787 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8929. Min Act: -0.1700
Data Index: 7863143 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8929. Min Act: -0.1700
Data Index: 1594804 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8617. Min Act: -0.1700
Data Index: 2942082 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8617. Min Act: -0.1700
Data Index: 2124813 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8617. Min Act: -0.1700
Data Index: 5672822 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8617. Min Act: -0.1700
Data Index: 813099 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8304. Min Act: -0.1700
Data Index: 2359869 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.8304. Min Act: -0.1700
Data Index: 5701155 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.7679. Min Act: -0.1700
Data Index: 6615485 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2992. Min Range: -6.2992
Max Act: 5.7992. Min Act: -0.1700
Data Index: 6309232 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19