Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4114 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1401. Min Range: -5.1401
Max Act: 5.1401. Min Act: -0.1700
Data Index: 6033449 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1401. Min Range: -5.1401
Max Act: 5.1088. Min Act: -0.1700
Data Index: 4030695 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1401. Min Range: -5.1401
Max Act: 5.0776. Min Act: -0.1700
Data Index: 1253924 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1401. Min Range: -5.1401
Max Act: 5.0776. Min Act: -0.1700
Data Index: 8403134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1401. Min Range: -5.1401
Max Act: 5.0151. Min Act: -0.1700
Data Index: 4870433 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9838. Min Act: -0.1700
Data Index: 3798317 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9838. Min Act: -0.1699
Data Index: 6420120 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9838. Min Act: -0.1700
Data Index: 6918147 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1700
Data Index: 1078327 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1699
Data Index: 1134266 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1700
Data Index: 678101 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9213. Min Act: -0.1700
Data Index: 2227915 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1686
Data Index: 2931688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1700
Data Index: 2386595 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1700
Data Index: 4136041 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1699
Data Index: 220791 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1700
Data Index: 5053049 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1699
Data Index: 880284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9526. Min Act: -0.1700
Data Index: 7301204 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1401. Min Range: -5.1401
Max Act: 4.9838. Min Act: -0.1700
Data Index: 6045934 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19