Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6387 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.9751. Min Act: -0.1700
Data Index: 1590940 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.9439. Min Act: -0.1700
Data Index: 7381143 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.9751. Min Act: -0.1700
Data Index: 3298373 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.9126. Min Act: -0.1700
Data Index: 8175471 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.9439. Min Act: -0.1700
Data Index: 6828515 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.9126. Min Act: -0.1700
Data Index: 4347660 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.9126. Min Act: -0.1700
Data Index: 1770110 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8814. Min Act: -0.1700
Data Index: 8284160 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8814. Min Act: -0.1700
Data Index: 6217448 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8814. Min Act: -0.1700
Data Index: 1343391 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8814. Min Act: -0.1700
Data Index: 7582847 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8501. Min Act: -0.1700
Data Index: 2018506 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8501. Min Act: -0.1700
Data Index: 4320507 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8814. Min Act: -0.1700
Data Index: 2372097 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8501. Min Act: -0.1700
Data Index: 2267681 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8188. Min Act: -0.1700
Data Index: 1550086 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8188. Min Act: -0.1700
Data Index: 3833317 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8188. Min Act: -0.1700
Data Index: 38467 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8188. Min Act: -0.1700
Data Index: 2713276 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9751. Min Range: -3.9751
Max Act: 3.8188. Min Act: -0.1700
Data Index: 1443221 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19