Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1881 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.8146. Min Act: -0.1700
Data Index: 6025295 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.8146. Min Act: -0.1700
Data Index: 4339526 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.7834. Min Act: -0.1700
Data Index: 2104985 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.7209. Min Act: -0.1700
Data Index: 5858868 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6584. Min Act: -0.1700
Data Index: 6652773 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6896. Min Act: -0.1700
Data Index: 7819328 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6896. Min Act: -0.1700
Data Index: 8103894 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6271. Min Act: -0.1700
Data Index: 6435542 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6271. Min Act: -0.1700
Data Index: 1588891 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6584. Min Act: -0.1700
Data Index: 7839165 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5959. Min Act: -0.1700
Data Index: 7412028 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6271. Min Act: -0.1700
Data Index: 1568055 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.6271. Min Act: -0.1700
Data Index: 2232624 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5646. Min Act: -0.1700
Data Index: 1789682 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5959. Min Act: -0.1700
Data Index: 797097 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5334. Min Act: -0.1700
Data Index: 2593964 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5334. Min Act: -0.1700
Data Index: 1881400 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5021. Min Act: -0.1700
Data Index: 4557073 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5021. Min Act: -0.1700
Data Index: 116884 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.5021. Min Act: -0.1700
Data Index: 6802233 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19