Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4349 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5232. Min Range: -4.5232
Max Act: 4.5232. Min Act: -0.1700
Data Index: 8137298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5232. Min Range: -4.5232
Max Act: 4.3357. Min Act: -0.1700
Data Index: 8137297 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5232. Min Range: -4.5232
Max Act: 4.2107. Min Act: -0.1700
Data Index: 6264918 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5232. Min Range: -4.5232
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1081987 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5232. Min Range: -4.5232
Max Act: 4.1169. Min Act: -0.1700
Data Index: 6561765 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5232. Min Range: -4.5232
Max Act: 4.0231. Min Act: -0.1700
Data Index: 8315830 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5232. Min Range: -4.5232
Max Act: 4.0231. Min Act: -0.1700
Data Index: 7349610 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.9919. Min Act: -0.1700
Data Index: 7666898 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.9294. Min Act: -0.1700
Data Index: 5671391 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8981. Min Act: -0.1700
Data Index: 1292899 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8981. Min Act: -0.1700
Data Index: 5965369 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8981. Min Act: -0.1700
Data Index: 3818781 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8668. Min Act: -0.1700
Data Index: 7557997 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8668. Min Act: -0.1700
Data Index: 5706404 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8668. Min Act: -0.1700
Data Index: 5374207 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8668. Min Act: -0.1700
Data Index: 6129663 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8356. Min Act: -0.1700
Data Index: 5795678 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8356. Min Act: -0.1700
Data Index: 4978722 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8043. Min Act: -0.1700
Data Index: 3695033 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5232. Min Range: -4.5232
Max Act: 3.8356. Min Act: -0.1700
Data Index: 6046700 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19