Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4545 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.2782. Min Act: -0.1700
Data Index: 2050156 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.1844. Min Act: -0.1700
Data Index: 8780363 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.1844. Min Act: -0.1700
Data Index: 2050158 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.0907. Min Act: -0.1700
Data Index: 5750958 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.0907. Min Act: -0.1700
Data Index: 5900902 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.0282. Min Act: -0.1700
Data Index: 5415642 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.0282. Min Act: -0.1700
Data Index: 7666496 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2782. Min Range: -5.2782
Max Act: 5.0282. Min Act: -0.1700
Data Index: 6011949 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9969. Min Act: -0.1700
Data Index: 3913859 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9969. Min Act: -0.1700
Data Index: 3151480 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9969. Min Act: -0.1700
Data Index: 6050745 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9657. Min Act: -0.1700
Data Index: 4175503 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9657. Min Act: -0.1700
Data Index: 1396549 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9657. Min Act: -0.1700
Data Index: 6530865 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9344. Min Act: -0.1700
Data Index: 4461948 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9032. Min Act: -0.1700
Data Index: 3558411 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9344. Min Act: -0.1700
Data Index: 3024868 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9344. Min Act: -0.1700
Data Index: 6697888 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9344. Min Act: -0.1700
Data Index: 6204035 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2782. Min Range: -5.2782
Max Act: 4.9344. Min Act: -0.1700
Data Index: 5450559 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19