Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7047. Min Range: -6.7047
Max Act: 6.7047. Min Act: -0.1700
Data Index: 3700543 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.8922. Min Act: -0.1700
Data Index: 7179818 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.8922. Min Act: -0.1700
Data Index: 961846 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.8610. Min Act: -0.1700
Data Index: 5848952 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.7360. Min Act: -0.1700
Data Index: 1146233 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.6735. Min Act: -0.1700
Data Index: 1508406 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.6422. Min Act: -0.1700
Data Index: 1604427 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.6110. Min Act: -0.1700
Data Index: 5869010 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5797. Min Act: -0.1700
Data Index: 8405430 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5485. Min Act: -0.1700
Data Index: 6964852 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 892126 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 7224742 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5485. Min Act: -0.1700
Data Index: 7224736 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 6593398 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 101137 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 7132716 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 2391468 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.4860. Min Act: -0.1700
Data Index: 2306694 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4350030 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7047. Min Range: -6.7047
Max Act: 5.4547. Min Act: -0.1700
Data Index: 5925864 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19