Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2078 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4821. Min Range: -6.4821
Max Act: 6.4821. Min Act: -0.1700
Data Index: 3520877 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4821. Min Range: -6.4821
Max Act: 6.3258. Min Act: -0.1700
Data Index: 7537912 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4821. Min Range: -6.4821
Max Act: 6.1383. Min Act: -0.1700
Data Index: 5027737 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4821. Min Range: -6.4821
Max Act: 6.1071. Min Act: -0.1700
Data Index: 1630143 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4821. Min Range: -6.4821
Max Act: 6.0758. Min Act: -0.1700
Data Index: 7422434 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4821. Min Range: -6.4821
Max Act: 6.0758. Min Act: -0.1700
Data Index: 8386639 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4821. Min Range: -6.4821
Max Act: 6.0133. Min Act: -0.1700
Data Index: 3124720 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.9508. Min Act: -0.1700
Data Index: 245025 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.9508. Min Act: -0.1700
Data Index: 6825340 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.9508. Min Act: -0.1700
Data Index: 1783374 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.9196. Min Act: -0.1700
Data Index: 6930341 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8883. Min Act: -0.1700
Data Index: 616236 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8883. Min Act: -0.1700
Data Index: 3799164 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8571. Min Act: -0.1700
Data Index: 1587010 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8571. Min Act: -0.1700
Data Index: 1647640 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8258. Min Act: -0.1700
Data Index: 3648662 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8258. Min Act: -0.1700
Data Index: 7999041 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8258. Min Act: -0.1700
Data Index: 4770082 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.8258. Min Act: -0.1700
Data Index: 5631121 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4821. Min Range: -6.4821
Max Act: 5.7946. Min Act: -0.1700
Data Index: 30699 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19