Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2182 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.9074. Min Act: -0.1694
Data Index: 4423089 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.8137. Min Act: -0.1700
Data Index: 2141528 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.8137. Min Act: -0.1700
Data Index: 6844695 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7824. Min Act: -0.1692
Data Index: 2244184 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7824. Min Act: -0.1700
Data Index: 1771880 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7824. Min Act: -0.1700
Data Index: 7415672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7824. Min Act: -0.1700
Data Index: 4109554 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1698
Data Index: 4144345 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7824. Min Act: -0.1700
Data Index: 4984580 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1696
Data Index: 3730969 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1669
Data Index: 7357319 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1685
Data Index: 6861794 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1698
Data Index: 5009528 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1700
Data Index: 6855232 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1698
Data Index: 2123597 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1700
Data Index: 1624625 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1699
Data Index: 5677510 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7512. Min Act: -0.1700
Data Index: 3896144 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7199. Min Act: -0.1700
Data Index: 1839150 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9074. Min Range: -5.9074
Max Act: 5.7199. Min Act: -0.1698
Data Index: 1102079 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19