Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5685. Min Act: -0.1700
Data Index: 3602856 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5215. Min Act: -0.1700
Data Index: 2598056 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4745. Min Act: -0.1700
Data Index: 5274607 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4118. Min Act: -0.1700
Data Index: 2590098 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4118. Min Act: -0.1700
Data Index: 8270855 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4118. Min Act: -0.1700
Data Index: 1834293 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 5867697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 6511246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 2756969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 5299923 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 8484286 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 4785140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 1571716 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3648. Min Act: -0.1700
Data Index: 5055661 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3334. Min Act: -0.1700
Data Index: 6849750 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3020. Min Act: -0.1700
Data Index: 4673761 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.3020. Min Act: -0.1700
Data Index: 6670604 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.2863. Min Act: -0.1700
Data Index: 5493530 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.2863. Min Act: -0.1700
Data Index: 7498989 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.2863. Min Act: -0.1700
Data Index: 2761061 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19