Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3953 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.9600. Min Act: -0.1700
Data Index: 6605389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.9430. Min Act: -0.1700
Data Index: 8164054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.9089. Min Act: -0.1700
Data Index: 3148147 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8919. Min Act: -0.1700
Data Index: 8425581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8748. Min Act: -0.1700
Data Index: 2243015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8748. Min Act: -0.1700
Data Index: 1934748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8577. Min Act: -0.1700
Data Index: 931909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8577. Min Act: -0.1700
Data Index: 6175845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8577. Min Act: -0.1700
Data Index: 8192171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8234. Min Act: -0.1700
Data Index: 8315390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8062. Min Act: -0.1700
Data Index: 7760312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8234. Min Act: -0.1700
Data Index: 2262366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8062. Min Act: -0.1700
Data Index: 7097177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8234. Min Act: -0.1700
Data Index: 7615609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8234. Min Act: -0.1700
Data Index: 4217355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8062. Min Act: -0.1700
Data Index: 2534078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8062. Min Act: -0.1700
Data Index: 1772110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8234. Min Act: -0.1700
Data Index: 3467013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8062. Min Act: -0.1700
Data Index: 7018076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9600. Min Range: -1.9600
Max Act: 1.8062. Min Act: -0.1700
Data Index: 1928567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19