Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3674. Min Range: -6.3674
Max Act: 6.3674. Min Act: -0.1700
Data Index: 2071963 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3674. Min Range: -6.3674
Max Act: 6.1174. Min Act: -0.1700
Data Index: 8031109 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3674. Min Range: -6.3674
Max Act: 6.0549. Min Act: -0.1700
Data Index: 949836 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3674. Min Range: -6.3674
Max Act: 6.0549. Min Act: -0.1700
Data Index: 1401215 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3674. Min Range: -6.3674
Max Act: 6.0237. Min Act: -0.1700
Data Index: 5167920 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.8987. Min Act: -0.1700
Data Index: 2659844 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.8987. Min Act: -0.1700
Data Index: 7333666 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.8987. Min Act: -0.1700
Data Index: 3223948 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.8674. Min Act: -0.1700
Data Index: 7699725 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.8049. Min Act: -0.1700
Data Index: 7765426 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.8049. Min Act: -0.1700
Data Index: 1590287 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.7737. Min Act: -0.1700
Data Index: 8323792 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.7424. Min Act: -0.1700
Data Index: 964672 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.7424. Min Act: -0.1700
Data Index: 8822806 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.7112. Min Act: -0.1700
Data Index: 1167137 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.7112. Min Act: -0.1700
Data Index: 2879899 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.7112. Min Act: -0.1700
Data Index: 6138784 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.6799. Min Act: -0.1700
Data Index: 5206056 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.6799. Min Act: -0.1700
Data Index: 7734815 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3674. Min Range: -6.3674
Max Act: 5.6174. Min Act: -0.1700
Data Index: 6521994 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19