Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.2097. Min Act: -0.1700
Data Index: 5056227 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.1599. Min Act: -0.1700
Data Index: 5056211 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.1265. Min Act: -0.1700
Data Index: 5468992 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.1265. Min Act: -0.1700
Data Index: 1998159 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.1098. Min Act: -0.1700
Data Index: 7005739 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0931. Min Act: -0.1700
Data Index: 1998142 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0763. Min Act: -0.1700
Data Index: 6462440 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0763. Min Act: -0.1700
Data Index: 4415485 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0763. Min Act: -0.1700
Data Index: 8070615 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0763. Min Act: -0.1700
Data Index: 8765351 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0595. Min Act: -0.1700
Data Index: 8686182 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0427. Min Act: -0.1700
Data Index: 8367965 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0595. Min Act: -0.1700
Data Index: 5047981 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0258. Min Act: -0.1700
Data Index: 5543162 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0427. Min Act: -0.1700
Data Index: 6757702 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0258. Min Act: -0.1700
Data Index: 6360731 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0090. Min Act: -0.1700
Data Index: 1443510 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0090. Min Act: -0.1700
Data Index: 8257192 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2097. Min Range: -2.2097
Max Act: 1.9921. Min Act: -0.1700
Data Index: 3604976 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2097. Min Range: -2.2097
Max Act: 2.0090. Min Act: -0.1700
Data Index: 8367963 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19