Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.9936. Min Act: -0.1700
Data Index: 3853190 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.9623. Min Act: -0.1700
Data Index: 3863388 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.8686. Min Act: -0.1700
Data Index: 8766256 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.8373. Min Act: -0.1700
Data Index: 2624938 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.8373. Min Act: -0.1697
Data Index: 3887479 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7748. Min Act: -0.1700
Data Index: 5779057 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7748. Min Act: -0.1700
Data Index: 2562292 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7436. Min Act: -0.1700
Data Index: 1584656 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7123. Min Act: -0.1700
Data Index: 6369070 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7123. Min Act: -0.1700
Data Index: 6950080 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7123. Min Act: -0.1700
Data Index: 4255480 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7123. Min Act: -0.1700
Data Index: 2815615 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7123. Min Act: -0.1700
Data Index: 3840258 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.7123. Min Act: -0.1700
Data Index: 1458567 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.6811. Min Act: -0.1700
Data Index: 8824876 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.6811. Min Act: -0.1700
Data Index: 3853189 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.6498. Min Act: -0.1700
Data Index: 2815614 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.6186. Min Act: -0.1700
Data Index: 8766255 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.6186. Min Act: -0.1700
Data Index: 3684068 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9936. Min Range: -4.9936
Max Act: 4.6186. Min Act: -0.1700
Data Index: 3483727 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19