Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.6423. Min Act: -0.1700
Data Index: 8063309 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.5134. Min Act: -0.1700
Data Index: 1081147 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.3833. Min Act: -0.1700
Data Index: 8080825 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.3178. Min Act: -0.1700
Data Index: 6490870 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2684. Min Act: -0.1700
Data Index: 1175606 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2519. Min Act: -0.1700
Data Index: 1798539 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2519. Min Act: -0.1700
Data Index: 1081140 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2354. Min Act: -0.1696
Data Index: 4931226 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2354. Min Act: -0.1700
Data Index: 7996637 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2188. Min Act: -0.1700
Data Index: 8603196 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2022. Min Act: -0.1700
Data Index: 5115566 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2188. Min Act: -0.1700
Data Index: 8438872 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2188. Min Act: -0.1700
Data Index: 835174 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2022. Min Act: -0.1700
Data Index: 7164295 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2022. Min Act: -0.1700
Data Index: 4354043 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2022. Min Act: -0.1700
Data Index: 3073863 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.1856. Min Act: -0.1700
Data Index: 5346171 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2188. Min Act: -0.1700
Data Index: 8324886 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.1856. Min Act: -0.1700
Data Index: 5402483 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6423. Min Range: -2.6423
Max Act: 2.2022. Min Act: -0.1700
Data Index: 7296066 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19