Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0051. Min Range: -7.0051
Max Act: 7.0051. Min Act: -0.1700
Data Index: 8399674 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.8488. Min Act: -0.1700
Data Index: 985862 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.7551. Min Act: -0.1700
Data Index: 4567872 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.7551. Min Act: -0.1700
Data Index: 8003519 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.7551. Min Act: -0.1700
Data Index: 7215638 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.7238. Min Act: -0.1700
Data Index: 7596609 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.7238. Min Act: -0.1700
Data Index: 3109274 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.6926. Min Act: -0.1700
Data Index: 8421351 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.6613. Min Act: -0.1700
Data Index: 4288331 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.6613. Min Act: -0.1700
Data Index: 7681518 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.6613. Min Act: -0.1700
Data Index: 5876710 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.6301. Min Act: -0.1700
Data Index: 2976254 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.6301. Min Act: -0.1700
Data Index: 2291147 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.6301. Min Act: -0.1700
Data Index: 5872129 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.5988. Min Act: -0.1700
Data Index: 4605454 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.5988. Min Act: -0.1700
Data Index: 5743573 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.5988. Min Act: -0.1700
Data Index: 4096654 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.5676. Min Act: -0.1700
Data Index: 352831 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.5363. Min Act: -0.1700
Data Index: 4374659 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0051. Min Range: -7.0051
Max Act: 6.5363. Min Act: -0.1700
Data Index: 398073 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19