Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5470. Min Range: -8.5470
Max Act: 8.5470. Min Act: -0.1700
Data Index: 8579982 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5470. Min Range: -8.5470
Max Act: 8.2970. Min Act: -0.1700
Data Index: 796131 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5470. Min Range: -8.5470
Max Act: 8.2345. Min Act: -0.1700
Data Index: 6078215 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5470. Min Range: -8.5470
Max Act: 8.2345. Min Act: -0.1700
Data Index: 2042625 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5470. Min Range: -8.5470
Max Act: 8.1720. Min Act: -0.1700
Data Index: 1961977 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5470. Min Range: -8.5470
Max Act: 8.0470. Min Act: -0.1700
Data Index: 2865713 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5470. Min Range: -8.5470
Max Act: 8.0470. Min Act: -0.1700
Data Index: 5273935 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.9845. Min Act: -0.1700
Data Index: 2359257 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.9845. Min Act: -0.1700
Data Index: 523483 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.9220. Min Act: -0.1700
Data Index: 6293088 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.9220. Min Act: -0.1700
Data Index: 5553640 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.8595. Min Act: -0.1700
Data Index: 8819388 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7970. Min Act: -0.1700
Data Index: 5512533 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7970. Min Act: -0.1700
Data Index: 89751 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7970. Min Act: -0.1700
Data Index: 7338527 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7970. Min Act: -0.1700
Data Index: 5363587 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7970. Min Act: -0.1700
Data Index: 1545698 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7970. Min Act: -0.1700
Data Index: 1164887 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7345. Min Act: -0.1700
Data Index: 2832303 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5470. Min Range: -8.5470
Max Act: 7.7345. Min Act: -0.1700
Data Index: 6193043 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19