Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2689. Min Range: -6.2689
Max Act: 6.2689. Min Act: -0.1700
Data Index: 5447299 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2689. Min Range: -6.2689
Max Act: 6.1752. Min Act: -0.1700
Data Index: 7998359 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2689. Min Range: -6.2689
Max Act: 6.1127. Min Act: -0.1700
Data Index: 8763820 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2689. Min Range: -6.2689
Max Act: 6.1439. Min Act: -0.1700
Data Index: 3548904 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2689. Min Range: -6.2689
Max Act: 6.0814. Min Act: -0.1700
Data Index: 3656813 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.8627. Min Act: -0.1700
Data Index: 8541091 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.8002. Min Act: -0.1700
Data Index: 1148793 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.8002. Min Act: -0.1700
Data Index: 1148792 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.7377. Min Act: -0.1700
Data Index: 2452473 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.7064. Min Act: -0.1700
Data Index: 6354392 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.6752. Min Act: -0.1700
Data Index: 5037795 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.7064. Min Act: -0.1700
Data Index: 4863482 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.6127. Min Act: -0.1700
Data Index: 1917903 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.5814. Min Act: -0.1700
Data Index: 2077355 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.6127. Min Act: -0.1700
Data Index: 176106 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.6127. Min Act: -0.1700
Data Index: 600106 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.6127. Min Act: -0.1700
Data Index: 7770631 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.6127. Min Act: -0.1700
Data Index: 2180123 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.5814. Min Act: -0.1700
Data Index: 277528 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2689. Min Range: -6.2689
Max Act: 5.5189. Min Act: -0.1700
Data Index: 607492 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19