Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6348 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.5375. Min Act: -0.1700
Data Index: 887877 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.4750. Min Act: -0.1700
Data Index: 2812738 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.4438. Min Act: -0.1700
Data Index: 8198134 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.4438. Min Act: -0.1700
Data Index: 5294911 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.4125. Min Act: -0.1700
Data Index: 652347 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.3500. Min Act: -0.1700
Data Index: 4407727 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.3188. Min Act: -0.1700
Data Index: 7391869 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.3188. Min Act: -0.1700
Data Index: 6712113 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.3188. Min Act: -0.1700
Data Index: 7013365 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.3188. Min Act: -0.1700
Data Index: 734143 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.2875. Min Act: -0.1700
Data Index: 7453913 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.2250. Min Act: -0.1700
Data Index: 7352797 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.2563. Min Act: -0.1700
Data Index: 4706074 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.1938. Min Act: -0.1700
Data Index: 4058415 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.2563. Min Act: -0.1700
Data Index: 484266 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.2250. Min Act: -0.1700
Data Index: 5073094 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.1938. Min Act: -0.1700
Data Index: 2553200 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.1938. Min Act: -0.1700
Data Index: 7733474 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.1938. Min Act: -0.1700
Data Index: 6375578 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5375. Min Range: -6.5375
Max Act: 6.1938. Min Act: -0.1700
Data Index: 2600951 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19