Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6701. Min Act: -0.1700
Data Index: 7607328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6701. Min Act: -0.1700
Data Index: 6108715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6701. Min Act: -0.1700
Data Index: 513426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6701. Min Act: -0.1700
Data Index: 6118912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6701. Min Act: -0.1700
Data Index: 8519730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6701. Min Act: -0.1700
Data Index: 8716021 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6388. Min Act: -0.1699
Data Index: 6853691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6388. Min Act: -0.1700
Data Index: 89521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6075. Min Act: -0.1700
Data Index: 3563431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6075. Min Act: -0.1700
Data Index: 842795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6075. Min Act: -0.1700
Data Index: 4445621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6075. Min Act: -0.1700
Data Index: 4434931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6075. Min Act: -0.1700
Data Index: 4364069 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6075. Min Act: -0.1700
Data Index: 1661233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.6388. Min Act: -0.1700
Data Index: 8400353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.5762. Min Act: -0.1700
Data Index: 2140883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.5762. Min Act: -0.1699
Data Index: 4498908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.5762. Min Act: -0.1700
Data Index: 2298129 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.5762. Min Act: -0.1700
Data Index: 4999086 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6701. Min Range: -3.6701
Max Act: 3.5762. Min Act: -0.1700
Data Index: 6962625 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19