Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.1816. Min Act: -0.1700
Data Index: 6611326 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0879. Min Act: -0.1700
Data Index: 7890121 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0566. Min Act: -0.1700
Data Index: 2220094 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0566. Min Act: -0.1700
Data Index: 8171906 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0254. Min Act: -0.1700
Data Index: 447570 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0566. Min Act: -0.1700
Data Index: 2001727 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0254. Min Act: -0.1700
Data Index: 4542789 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9316. Min Act: -0.1700
Data Index: 7949397 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9941. Min Act: -0.1700
Data Index: 7964655 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0566. Min Act: -0.1700
Data Index: 3974249 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9629. Min Act: -0.1700
Data Index: 3786690 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9941. Min Act: -0.1700
Data Index: 4301623 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9941. Min Act: -0.1700
Data Index: 8792713 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9004. Min Act: -0.1700
Data Index: 1525786 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0254. Min Act: -0.1700
Data Index: 443426 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1816. Min Range: -5.1816
Max Act: 5.0254. Min Act: -0.1700
Data Index: 6666776 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9004. Min Act: -0.1700
Data Index: 1865023 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9629. Min Act: -0.1700
Data Index: 6965863 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9629. Min Act: -0.1700
Data Index: 2846345 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1816. Min Range: -5.1816
Max Act: 4.9941. Min Act: -0.1700
Data Index: 100606 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19