Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.8027. Min Act: -0.1700
Data Index: 2842428 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.7402. Min Act: -0.1700
Data Index: 7302043 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.7402. Min Act: -0.1700
Data Index: 6628408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.6777. Min Act: -0.1700
Data Index: 49112 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.7090. Min Act: -0.1700
Data Index: 4493088 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.6777. Min Act: -0.1700
Data Index: 4240515 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.6465. Min Act: -0.1700
Data Index: 8421281 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.6465. Min Act: -0.1700
Data Index: 4186846 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5840. Min Act: -0.1700
Data Index: 5169586 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.6152. Min Act: -0.1700
Data Index: 6666267 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5840. Min Act: -0.1700
Data Index: 3056615 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5840. Min Act: -0.1700
Data Index: 5365307 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5527. Min Act: -0.1700
Data Index: 780803 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5840. Min Act: -0.1700
Data Index: 3552628 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5840. Min Act: -0.1700
Data Index: 4812947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5527. Min Act: -0.1700
Data Index: 7762683 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5527. Min Act: -0.1700
Data Index: 1698871 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5527. Min Act: -0.1700
Data Index: 3862142 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5215. Min Act: -0.1700
Data Index: 771521 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8027. Min Range: -4.8027
Max Act: 4.5215. Min Act: -0.1700
Data Index: 785825 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19