Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6389 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5068. Min Range: -4.5068
Max Act: 4.5068. Min Act: -0.1700
Data Index: 4119410 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5068. Min Range: -4.5068
Max Act: 4.2880. Min Act: -0.1700
Data Index: 2612381 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5068. Min Range: -4.5068
Max Act: 4.0692. Min Act: -0.1700
Data Index: 7707199 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5068. Min Range: -4.5068
Max Act: 4.0067. Min Act: -0.1700
Data Index: 7212931 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5068. Min Range: -4.5068
Max Act: 4.0380. Min Act: -0.1700
Data Index: 5804707 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5068. Min Range: -4.5068
Max Act: 4.0067. Min Act: -0.1700
Data Index: 3297470 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9754. Min Act: -0.1700
Data Index: 6539856 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9754. Min Act: -0.1700
Data Index: 4211869 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9754. Min Act: -0.1700
Data Index: 5871310 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9754. Min Act: -0.1700
Data Index: 4254549 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9754. Min Act: -0.1700
Data Index: 6266550 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 1911066 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 6396203 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 1381873 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 6539857 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 7531010 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 5574374 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 6052582 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9598. Min Act: -0.1700
Data Index: 7385692 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5068. Min Range: -4.5068
Max Act: 3.9285. Min Act: -0.1700
Data Index: 6439828 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19