Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 284 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 1534385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 8778995 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 8613035 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 8611919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 8130386 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 8057001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 7880525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 6781141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 6682014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 5723508 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 5717501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 57874 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 5655568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 4645027 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 3039405 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 2910098 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 2050374 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 1621525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3235. Min Act: -0.1700
Data Index: 1501218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3235. Min Range: -4.3235
Max Act: 4.3079. Min Act: -0.1700
Data Index: 1301062 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19