Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2550 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5182. Min Range: -8.5182
Max Act: 8.5182. Min Act: -0.1700
Data Index: 3113272 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.3932. Min Act: -0.1700
Data Index: 6664521 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.2369. Min Act: -0.1700
Data Index: 1850001 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.2057. Min Act: -0.1700
Data Index: 70902 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.2057. Min Act: -0.1700
Data Index: 4594656 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.2057. Min Act: -0.1700
Data Index: 8787273 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.1432. Min Act: -0.1700
Data Index: 8104143 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.0494. Min Act: -0.1700
Data Index: 5473255 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5182. Min Range: -8.5182
Max Act: 7.0182. Min Act: -0.1700
Data Index: 8453719 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.9557. Min Act: -0.1700
Data Index: 2474041 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.9244. Min Act: -0.1700
Data Index: 1094908 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.9244. Min Act: -0.1700
Data Index: 4928562 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8932. Min Act: -0.1700
Data Index: 7645197 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8932. Min Act: -0.1700
Data Index: 3166607 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8307. Min Act: -0.1700
Data Index: 5024647 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8619. Min Act: -0.1700
Data Index: 6110048 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8619. Min Act: -0.1700
Data Index: 2382888 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8307. Min Act: -0.1700
Data Index: 4318598 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8307. Min Act: -0.1700
Data Index: 4201272 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5182. Min Range: -8.5182
Max Act: 6.8307. Min Act: -0.1700
Data Index: 8241696 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19