Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5616 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4622. Min Range: -6.4622
Max Act: 6.4622. Min Act: -0.1700
Data Index: 6827143 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4622. Min Range: -6.4622
Max Act: 6.0559. Min Act: -0.1700
Data Index: 8755160 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.9309. Min Act: -0.1700
Data Index: 3714411 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.9309. Min Act: -0.1700
Data Index: 2644255 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.9309. Min Act: -0.1700
Data Index: 5971932 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8997. Min Act: -0.1700
Data Index: 3527735 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8997. Min Act: -0.1700
Data Index: 7094542 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8997. Min Act: -0.1700
Data Index: 4297367 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8372. Min Act: -0.1700
Data Index: 920415 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8372. Min Act: -0.1700
Data Index: 2783468 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8372. Min Act: -0.1700
Data Index: 8781240 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8059. Min Act: -0.1700
Data Index: 7636080 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8059. Min Act: -0.1700
Data Index: 8736606 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8059. Min Act: -0.1700
Data Index: 6087489 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8059. Min Act: -0.1700
Data Index: 370471 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8059. Min Act: -0.1700
Data Index: 183823 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.7747. Min Act: -0.1700
Data Index: 166146 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.7747. Min Act: -0.1700
Data Index: 1974387 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.7747. Min Act: -0.1700
Data Index: 6655660 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4622. Min Range: -6.4622
Max Act: 5.8059. Min Act: -0.1700
Data Index: 654087 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19