Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.8383. Min Act: -0.1700
Data Index: 8243297 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.6508. Min Act: -0.1700
Data Index: 1688583 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.2133. Min Act: -0.1700
Data Index: 5891067 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.2133. Min Act: -0.1700
Data Index: 4274664 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.1821. Min Act: -0.1700
Data Index: 2378033 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.1821. Min Act: -0.1700
Data Index: 8000724 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.1196. Min Act: -0.1700
Data Index: 1688582 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.1196. Min Act: -0.1700
Data Index: 384968 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.1196. Min Act: -0.1700
Data Index: 5091270 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.0571. Min Act: -0.1700
Data Index: 2976556 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.0571. Min Act: -0.1700
Data Index: 3808404 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.0571. Min Act: -0.1700
Data Index: 7948251 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.0883. Min Act: -0.1694
Data Index: 5891079 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.0258. Min Act: -0.1700
Data Index: 3459599 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8383. Min Range: -6.8383
Max Act: 6.0258. Min Act: -0.1700
Data Index: 1223581 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8383. Min Range: -6.8383
Max Act: 5.9008. Min Act: -0.1700
Data Index: 4271166 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8383. Min Range: -6.8383
Max Act: 5.9008. Min Act: -0.1698
Data Index: 5397728 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8383. Min Range: -6.8383
Max Act: 5.8696. Min Act: -0.1700
Data Index: 5428792 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8383. Min Range: -6.8383
Max Act: 5.8696. Min Act: -0.1700
Data Index: 5344867 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8383. Min Range: -6.8383
Max Act: 5.8383. Min Act: -0.1700
Data Index: 4810137 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19