Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 44.7548. Min Range: -44.7548
Max Act: 44.7548. Min Act: -0.1700
Data Index: 4122579 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 44.7548. Min Range: -44.7548
Max Act: 44.5048. Min Act: -0.1700
Data Index: 5688697 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 44.7548. Min Range: -44.7548
Max Act: 44.2548. Min Act: -0.1700
Data Index: 1584480 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 44.7548. Min Range: -44.7548
Max Act: 44.0048. Min Act: -0.1700
Data Index: 4657913 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 44.7548. Min Range: -44.7548
Max Act: 44.0048. Min Act: -0.1700
Data Index: 1292045 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.7548. Min Act: -0.1700
Data Index: 1722814 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.7548. Min Act: -0.1700
Data Index: 441651 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.7548. Min Act: -0.1700
Data Index: 1360615 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 2935409 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 3774224 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 5197494 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 1083522 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 3473012 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 3464485 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 5012152 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 4993809 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 4693087 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 1858036 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 267068 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 44.7548. Min Range: -44.7548
Max Act: 43.5048. Min Act: -0.1700
Data Index: 3807407 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19