Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.1063. Min Act: -0.1700
Data Index: 4560740 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 5721554 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 1047320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 5440258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 2071773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 8066351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 6578236 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 4214008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 3214494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 7950813 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 5276113 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 8130285 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 5163549 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 7398052 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 5626649 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 385090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0125. Min Act: -0.1700
Data Index: 5665757 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0125. Min Act: -0.1700
Data Index: 5520158 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1063. Min Range: -4.1063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 2143348 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1063. Min Range: -4.1063
Max Act: 3.9812. Min Act: -0.1700
Data Index: 6121569 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19