Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.1011. Min Act: -0.1700
Data Index: 2217117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0386. Min Act: -0.1700
Data Index: 3986675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0386. Min Act: -0.1700
Data Index: 2726833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0386. Min Act: -0.1700
Data Index: 2415362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0073. Min Act: -0.1700
Data Index: 5950539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0073. Min Act: -0.1700
Data Index: 6198177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0073. Min Act: -0.1700
Data Index: 6464295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0073. Min Act: -0.1700
Data Index: 2963345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0073. Min Act: -0.1700
Data Index: 1000585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1011. Min Range: -4.1011
Max Act: 4.0073. Min Act: -0.1700
Data Index: 8434820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 469648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 955960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 3592060 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 2267750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9448. Min Act: -0.1700
Data Index: 2196215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9760. Min Act: -0.1700
Data Index: 4372470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9135. Min Act: -0.1700
Data Index: 3955950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9448. Min Act: -0.1700
Data Index: 2485691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9448. Min Act: -0.1700
Data Index: 1253858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1011. Min Range: -4.1011
Max Act: 3.9448. Min Act: -0.1700
Data Index: 1297555 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19