Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0688. Min Range: -4.0688
Max Act: 4.0688. Min Act: -0.1700
Data Index: 6194164 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0688. Min Range: -4.0688
Max Act: 4.0063. Min Act: -0.1700
Data Index: 6464030 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0688. Min Range: -4.0688
Max Act: 4.0063. Min Act: -0.1700
Data Index: 267245 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.9750. Min Act: -0.1700
Data Index: 5542672 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.9750. Min Act: -0.1700
Data Index: 6182382 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.9438. Min Act: -0.1700
Data Index: 8470253 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.9125. Min Act: -0.1700
Data Index: 8548550 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.9125. Min Act: -0.1700
Data Index: 2378310 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.9125. Min Act: -0.1700
Data Index: 8304469 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8812. Min Act: -0.1700
Data Index: 4057003 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8812. Min Act: -0.1700
Data Index: 905566 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8812. Min Act: -0.1700
Data Index: 7425265 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8500. Min Act: -0.1700
Data Index: 4816359 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8187. Min Act: -0.1700
Data Index: 2397430 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8500. Min Act: -0.1700
Data Index: 1560753 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8187. Min Act: -0.1700
Data Index: 2678662 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8187. Min Act: -0.1700
Data Index: 6699833 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8343. Min Act: -0.1700
Data Index: 7904651 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.8031. Min Act: -0.1700
Data Index: 4606740 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0688. Min Range: -4.0688
Max Act: 3.7874. Min Act: -0.1700
Data Index: 8239516 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19