Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 369 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0064. Min Range: -7.0064
Max Act: 7.0064. Min Act: -0.1700
Data Index: 3064715 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.8502. Min Act: -0.1700
Data Index: 5561201 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.7877. Min Act: -0.1700
Data Index: 4824005 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.7877. Min Act: -0.1700
Data Index: 5055325 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.5689. Min Act: -0.1700
Data Index: 1127863 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.5064. Min Act: -0.1700
Data Index: 575893 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.4439. Min Act: -0.1700
Data Index: 5636418 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.4127. Min Act: -0.1700
Data Index: 294063 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.4127. Min Act: -0.1700
Data Index: 1807650 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.4439. Min Act: -0.1700
Data Index: 6414983 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3814. Min Act: -0.1700
Data Index: 1267118 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3814. Min Act: -0.1700
Data Index: 8140267 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3814. Min Act: -0.1700
Data Index: 1944600 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3502. Min Act: -0.1700
Data Index: 6928097 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3189. Min Act: -0.1700
Data Index: 1146062 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3189. Min Act: -0.1700
Data Index: 8731745 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.2877. Min Act: -0.1700
Data Index: 2675167 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3189. Min Act: -0.1700
Data Index: 930976 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.2877. Min Act: -0.1700
Data Index: 4771360 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0064. Min Range: -7.0064
Max Act: 6.3189. Min Act: -0.1700
Data Index: 4585316 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19