Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1812. Min Range: -11.1812
Max Act: 11.1812. Min Act: -0.1700
Data Index: 3700346 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1812. Min Range: -11.1812
Max Act: 11.1187. Min Act: -0.1700
Data Index: 3041256 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.9937. Min Act: -0.1700
Data Index: 7564902 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.7437. Min Act: -0.1700
Data Index: 1310275 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.8062. Min Act: -0.1700
Data Index: 863770 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.7437. Min Act: -0.1700
Data Index: 1596297 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.6812. Min Act: -0.1700
Data Index: 1724988 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.6187. Min Act: -0.1700
Data Index: 1990356 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.6187. Min Act: -0.1700
Data Index: 5301601 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.5562. Min Act: -0.1700
Data Index: 3948315 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.5562. Min Act: -0.1700
Data Index: 2674191 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.5562. Min Act: -0.1700
Data Index: 5870759 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.4937. Min Act: -0.1700
Data Index: 5908052 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.4312. Min Act: -0.1700
Data Index: 2567716 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.4312. Min Act: -0.1700
Data Index: 1569909 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.4312. Min Act: -0.1700
Data Index: 4101976 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.3687. Min Act: -0.1700
Data Index: 6901595 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.3062. Min Act: -0.1700
Data Index: 6587573 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.3687. Min Act: -0.1700
Data Index: 7545888 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1812. Min Range: -11.1812
Max Act: 10.3687. Min Act: -0.1700
Data Index: 4736940 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19