Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3311. Min Range: -8.3311
Max Act: 8.3311. Min Act: -0.1700
Data Index: 1008962 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3311. Min Range: -8.3311
Max Act: 8.0811. Min Act: -0.1700
Data Index: 5583800 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3311. Min Range: -8.3311
Max Act: 8.0811. Min Act: -0.1700
Data Index: 1764645 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3311. Min Range: -8.3311
Max Act: 8.0186. Min Act: -0.1700
Data Index: 300075 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.9561. Min Act: -0.1700
Data Index: 3640086 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.9561. Min Act: -0.1700
Data Index: 2195412 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.8936. Min Act: -0.1700
Data Index: 8341134 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.9561. Min Act: -0.1700
Data Index: 8352328 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.9561. Min Act: -0.1700
Data Index: 7743111 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.8936. Min Act: -0.1700
Data Index: 8179011 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.8624. Min Act: -0.1700
Data Index: 4703842 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.8936. Min Act: -0.1700
Data Index: 1969107 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.8311. Min Act: -0.1700
Data Index: 1588071 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.7686. Min Act: -0.1700
Data Index: 2297842 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.7999. Min Act: -0.1700
Data Index: 7609702 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.7374. Min Act: -0.1700
Data Index: 7353878 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.7686. Min Act: -0.1700
Data Index: 6167275 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.7374. Min Act: -0.1700
Data Index: 702982 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.7374. Min Act: -0.1700
Data Index: 7671990 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3311. Min Range: -8.3311
Max Act: 7.7374. Min Act: -0.1700
Data Index: 4156389 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19