Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1476 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.7031. Min Act: -0.1700
Data Index: 3727041 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.4531. Min Act: -0.1700
Data Index: 3529892 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.2656. Min Act: -0.1700
Data Index: 5367543 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.2344. Min Act: -0.1700
Data Index: 3090391 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.2656. Min Act: -0.1700
Data Index: 6645154 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 8690873 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.1719. Min Act: -0.1700
Data Index: 4792240 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.1406. Min Act: -0.1699
Data Index: 5313468 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.1406. Min Act: -0.1700
Data Index: 2509669 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0781. Min Act: -0.1700
Data Index: 5485589 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0781. Min Act: -0.1700
Data Index: 5850380 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.1094. Min Act: -0.1700
Data Index: 509730 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0469. Min Act: -0.1700
Data Index: 2228713 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0469. Min Act: -0.1700
Data Index: 8174759 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0781. Min Act: -0.1700
Data Index: 4032819 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 2493753 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0469. Min Act: -0.1700
Data Index: 3374019 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 6194353 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 682674 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7031. Min Range: -6.7031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 5727274 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19