Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0017. Min Range: -7.0017
Max Act: 7.0017. Min Act: -0.1700
Data Index: 2529455 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0017. Min Range: -7.0017
Max Act: 7.0017. Min Act: -0.1700
Data Index: 6597055 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.9704. Min Act: -0.1700
Data Index: 6521107 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.8142. Min Act: -0.1700
Data Index: 6263749 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.7829. Min Act: -0.1700
Data Index: 3617294 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.7517. Min Act: -0.1700
Data Index: 3954963 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.6892. Min Act: -0.1700
Data Index: 6830500 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.6267. Min Act: -0.1700
Data Index: 7174415 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5642. Min Act: -0.1700
Data Index: 5419257 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5642. Min Act: -0.1700
Data Index: 3067885 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5642. Min Act: -0.1700
Data Index: 6408983 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5329. Min Act: -0.1700
Data Index: 3147731 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5017. Min Act: -0.1700
Data Index: 8616620 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5017. Min Act: -0.1700
Data Index: 614968 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5329. Min Act: -0.1700
Data Index: 2595018 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5329. Min Act: -0.1700
Data Index: 826784 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5329. Min Act: -0.1700
Data Index: 2917120 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5017. Min Act: -0.1700
Data Index: 4810682 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5017. Min Act: -0.1700
Data Index: 2353251 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0017. Min Range: -7.0017
Max Act: 6.5017. Min Act: -0.1700
Data Index: 266674 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19