Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.5075. Min Act: -0.1700
Data Index: 4435283 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.5075. Min Act: -0.1700
Data Index: 1197820 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4762. Min Act: -0.1700
Data Index: 1520193 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4762. Min Act: -0.1700
Data Index: 7146891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3142566 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4135. Min Act: -0.1700
Data Index: 944997 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 128566 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4135. Min Act: -0.1700
Data Index: 1530172 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 2568705 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3696928 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 4952284 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 25747 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 5031051 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3028591 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3552223 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 202824 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3137184 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 6101488 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 2077414 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5075. Min Range: -3.5075
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3367630 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19