Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.2577. Min Act: -0.1700
Data Index: 4852781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.1327. Min Act: -0.1700
Data Index: 2033372 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0389. Min Act: -0.1700
Data Index: 3121463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0389. Min Act: -0.1700
Data Index: 2209751 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0077. Min Act: -0.1700
Data Index: 4518470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0077. Min Act: -0.1700
Data Index: 7713738 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0077. Min Act: -0.1700
Data Index: 4566105 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0077. Min Act: -0.1700
Data Index: 2737814 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0077. Min Act: -0.1700
Data Index: 2568773 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2577. Min Range: -4.2577
Max Act: 4.0077. Min Act: -0.1700
Data Index: 4057195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 2925172 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 2910163 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 7710276 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9451. Min Act: -0.1700
Data Index: 4255938 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 7669733 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 5824428 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 3802898 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 5141091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 3384713 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2577. Min Range: -4.2577
Max Act: 3.9764. Min Act: -0.1700
Data Index: 3317487 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19