Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0621. Min Range: -8.0621
Max Act: 8.0621. Min Act: -0.1700
Data Index: 5779550 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0621. Min Range: -8.0621
Max Act: 8.0621. Min Act: -0.1700
Data Index: 5558702 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.9371. Min Act: -0.1700
Data Index: 1173368 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.9371. Min Act: -0.1700
Data Index: 5253844 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.6871. Min Act: -0.1700
Data Index: 4745920 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.6871. Min Act: -0.1700
Data Index: 7206710 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.6871. Min Act: -0.1700
Data Index: 6319868 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.6871. Min Act: -0.1700
Data Index: 5283455 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.6871. Min Act: -0.1700
Data Index: 3997383 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.6246. Min Act: -0.1700
Data Index: 3438381 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.5621. Min Act: -0.1700
Data Index: 590142 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.5621. Min Act: -0.1700
Data Index: 5249779 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.5309. Min Act: -0.1700
Data Index: 5693261 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.5309. Min Act: -0.1700
Data Index: 8789171 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.4996. Min Act: -0.1700
Data Index: 359017 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.4684. Min Act: -0.1700
Data Index: 1412703 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.4371. Min Act: -0.1700
Data Index: 4353105 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.4059. Min Act: -0.1700
Data Index: 515962 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.3746. Min Act: -0.1700
Data Index: 8155388 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0621. Min Range: -8.0621
Max Act: 7.3746. Min Act: -0.1700
Data Index: 4706365 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19