Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5172 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.2024. Min Act: -0.1700
Data Index: 5067786 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.2024. Min Act: -0.1700
Data Index: 26541 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7943763 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1712. Min Act: -0.1700
Data Index: 7586726 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1399. Min Act: -0.1700
Data Index: 7834939 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 1957621 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1399. Min Act: -0.1700
Data Index: 897401 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1399. Min Act: -0.1700
Data Index: 7109346 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 547833 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 7074163 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 3380561 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 1788298 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 7059104 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 3198766 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 6902974 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 6451663 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 5925278 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 2641549 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1087. Min Act: -0.1700
Data Index: 2322791 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2024. Min Range: -4.2024
Max Act: 4.1399. Min Act: -0.1700
Data Index: 5210905 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19