Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3018 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.5914. Min Act: -0.1700
Data Index: 5437513 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.5914. Min Act: -0.1700
Data Index: 3492765 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4977. Min Act: -0.1700
Data Index: 4913166 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4977. Min Act: -0.1700
Data Index: 4573334 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4977. Min Act: -0.1700
Data Index: 1065292 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4664. Min Act: -0.1700
Data Index: 3195247 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4664. Min Act: -0.1700
Data Index: 2369767 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4664. Min Act: -0.1700
Data Index: 4012963 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4664. Min Act: -0.1700
Data Index: 4428321 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4039. Min Act: -0.1700
Data Index: 8302111 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1353699 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3727. Min Act: -0.1700
Data Index: 7318591 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3727. Min Act: -0.1700
Data Index: 1652450 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3727. Min Act: -0.1700
Data Index: 7427686 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3102. Min Act: -0.1700
Data Index: 1594747 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.3102. Min Act: -0.1700
Data Index: 8247699 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6431225 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.2789. Min Act: -0.1700
Data Index: 4269587 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.2477. Min Act: -0.1700
Data Index: 2977676 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5914. Min Range: -5.5914
Max Act: 5.2164. Min Act: -0.1700
Data Index: 8031121 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19