Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.8207. Min Act: -0.1700
Data Index: 6793970 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7581. Min Act: -0.1698
Data Index: 4571691 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7268. Min Act: -0.1700
Data Index: 3653101 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7268. Min Act: -0.1700
Data Index: 6327953 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6955. Min Act: -0.1700
Data Index: 98879 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6955. Min Act: -0.1700
Data Index: 4803791 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6643. Min Act: -0.1700
Data Index: 5386396 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6643. Min Act: -0.1700
Data Index: 8250689 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6643. Min Act: -0.1700
Data Index: 8339976 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6330. Min Act: -0.1698
Data Index: 4463280 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6017. Min Act: -0.1700
Data Index: 8132153 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6330. Min Act: -0.1700
Data Index: 579343 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6330. Min Act: -0.1700
Data Index: 762771 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6330. Min Act: -0.1700
Data Index: 6027928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6330. Min Act: -0.1700
Data Index: 4414389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6330. Min Act: -0.1700
Data Index: 1041617 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6017. Min Act: -0.1700
Data Index: 1727629 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6017. Min Act: -0.1700
Data Index: 3329438 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6017. Min Act: -0.1700
Data Index: 467909 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6017. Min Act: -0.1699
Data Index: 6800244 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19