Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1897 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.6430. Min Act: -0.1700
Data Index: 6703166 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.4555. Min Act: -0.1700
Data Index: 51888 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.4243. Min Act: -0.1700
Data Index: 6238427 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.3618. Min Act: -0.1700
Data Index: 5180169 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3509089 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.2993. Min Act: -0.1700
Data Index: 8732944 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.2055. Min Act: -0.1700
Data Index: 1070156 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.1430. Min Act: -0.1700
Data Index: 6192447 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.1430. Min Act: -0.1700
Data Index: 789332 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.1430. Min Act: -0.1700
Data Index: 5814755 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.1118. Min Act: -0.1700
Data Index: 1912165 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.1118. Min Act: -0.1700
Data Index: 3950403 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.0805. Min Act: -0.1700
Data Index: 3818721 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.0493. Min Act: -0.1700
Data Index: 798916 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.0805. Min Act: -0.1700
Data Index: 3676674 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.0493. Min Act: -0.1700
Data Index: 4752113 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.0180. Min Act: -0.1700
Data Index: 561000 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6430. Min Range: -5.6430
Max Act: 5.0180. Min Act: -0.1700
Data Index: 3655338 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6430. Min Range: -5.6430
Max Act: 4.9555. Min Act: -0.1700
Data Index: 464069 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6430. Min Range: -5.6430
Max Act: 4.9868. Min Act: -0.1700
Data Index: 4286563 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19