Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.9005. Min Act: -0.1700
Data Index: 3243963 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7805. Min Act: -0.1700
Data Index: 6784122 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7114. Min Act: -0.1700
Data Index: 6449679 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7114. Min Act: -0.1700
Data Index: 6894114 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7114. Min Act: -0.1700
Data Index: 3287104 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7114. Min Act: -0.1700
Data Index: 6808841 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7114. Min Act: -0.1700
Data Index: 3184436 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6941. Min Act: -0.1700
Data Index: 3017697 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6767. Min Act: -0.1700
Data Index: 3094520 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6767. Min Act: -0.1700
Data Index: 5247480 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6593. Min Act: -0.1700
Data Index: 1268276 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6419. Min Act: -0.1700
Data Index: 8365115 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6593. Min Act: -0.1700
Data Index: 7855520 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6593. Min Act: -0.1700
Data Index: 3254951 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6593. Min Act: -0.1700
Data Index: 8376647 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6593. Min Act: -0.1700
Data Index: 7680141 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6593. Min Act: -0.1700
Data Index: 2854405 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6419. Min Act: -0.1700
Data Index: 8310977 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6419. Min Act: -0.1700
Data Index: 5026728 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6419. Min Act: -0.1700
Data Index: 4637311 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19