Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0031. Min Range: -7.0031
Max Act: 7.0031. Min Act: -0.1700
Data Index: 2452728 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.6594. Min Act: -0.1700
Data Index: 8021740 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.4094. Min Act: -0.1700
Data Index: 7099437 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.3781. Min Act: -0.1700
Data Index: 6201490 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.3469. Min Act: -0.1700
Data Index: 8778950 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.3469. Min Act: -0.1700
Data Index: 150304 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.3156. Min Act: -0.1700
Data Index: 2818588 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.3156. Min Act: -0.1700
Data Index: 1333322 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.1906. Min Act: -0.1700
Data Index: 3528625 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.1906. Min Act: -0.1700
Data Index: 8038328 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.1281. Min Act: -0.1700
Data Index: 4499785 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.0969. Min Act: -0.1700
Data Index: 2783861 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.0969. Min Act: -0.1700
Data Index: 3033506 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.0656. Min Act: -0.1700
Data Index: 8147684 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.0344. Min Act: -0.1700
Data Index: 3258593 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.0344. Min Act: -0.1700
Data Index: 7859662 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.0031. Min Act: -0.1700
Data Index: 5357303 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0031. Min Range: -7.0031
Max Act: 6.0344. Min Act: -0.1700
Data Index: 2833268 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0031. Min Range: -7.0031
Max Act: 5.9719. Min Act: -0.1700
Data Index: 550429 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0031. Min Range: -7.0031
Max Act: 5.9406. Min Act: -0.1700
Data Index: 4697639 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19