Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4425 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0375. Min Range: -6.0375
Max Act: 6.0375. Min Act: -0.1700
Data Index: 5220988 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.8813. Min Act: -0.1700
Data Index: 5631367 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.9125. Min Act: -0.1700
Data Index: 5220989 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.8813. Min Act: -0.1700
Data Index: 705828 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.8813. Min Act: -0.1700
Data Index: 1445802 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.8188. Min Act: -0.1700
Data Index: 4475697 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.8188. Min Act: -0.1700
Data Index: 7323062 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7875. Min Act: -0.1700
Data Index: 5682684 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7875. Min Act: -0.1700
Data Index: 5547139 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7875. Min Act: -0.1700
Data Index: 3138011 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7563. Min Act: -0.1700
Data Index: 5171018 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7563. Min Act: -0.1700
Data Index: 5514242 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7563. Min Act: -0.1700
Data Index: 327877 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7250. Min Act: -0.1700
Data Index: 8688399 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7250. Min Act: -0.1700
Data Index: 5406337 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7563. Min Act: -0.1700
Data Index: 994755 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.7250. Min Act: -0.1700
Data Index: 6970876 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.6625. Min Act: -0.1700
Data Index: 5193926 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.6938. Min Act: -0.1700
Data Index: 3128693 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0375. Min Range: -6.0375
Max Act: 5.6938. Min Act: -0.1700
Data Index: 2000448 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19