Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5379 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.8981. Min Act: -0.1700
Data Index: 3773143 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.8512. Min Act: -0.1700
Data Index: 1561808 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.8668. Min Act: -0.1700
Data Index: 2226341 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.8668. Min Act: -0.1700
Data Index: 1814527 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.8512. Min Act: -0.1700
Data Index: 5119185 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7886. Min Act: -0.1700
Data Index: 1103248 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7730. Min Act: -0.1700
Data Index: 6432265 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7573. Min Act: -0.1700
Data Index: 2620668 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7573. Min Act: -0.1700
Data Index: 3591894 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7730. Min Act: -0.1700
Data Index: 5793727 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7573. Min Act: -0.1700
Data Index: 8651690 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7573. Min Act: -0.1700
Data Index: 1836928 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7417. Min Act: -0.1700
Data Index: 4122901 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7417. Min Act: -0.1700
Data Index: 2213167 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7261. Min Act: -0.1700
Data Index: 8403454 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7261. Min Act: -0.1700
Data Index: 6648334 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7104. Min Act: -0.1700
Data Index: 6488546 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.6948. Min Act: -0.1700
Data Index: 966606 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.7104. Min Act: -0.1700
Data Index: 6816340 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8981. Min Range: -3.8981
Max Act: 3.6948. Min Act: -0.1700
Data Index: 5064230 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19