Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.8434. Min Act: -0.1700
Data Index: 918136 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7809. Min Act: -0.1700
Data Index: 3481618 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7652. Min Act: -0.1700
Data Index: 5808554 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7809. Min Act: -0.1700
Data Index: 6807073 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7652. Min Act: -0.1700
Data Index: 1952699 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7496. Min Act: -0.1700
Data Index: 3104220 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7340. Min Act: -0.1700
Data Index: 5972281 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7183. Min Act: -0.1700
Data Index: 2978957 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7027. Min Act: -0.1700
Data Index: 2558748 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.7027. Min Act: -0.1700
Data Index: 4580219 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6714. Min Act: -0.1700
Data Index: 4215918 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6557. Min Act: -0.1700
Data Index: 1257225 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6714. Min Act: -0.1700
Data Index: 7990136 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6714. Min Act: -0.1700
Data Index: 3546670 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6714. Min Act: -0.1700
Data Index: 242666 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6557. Min Act: -0.1700
Data Index: 1938022 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6401. Min Act: -0.1700
Data Index: 4846640 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6401. Min Act: -0.1700
Data Index: 1362298 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6557. Min Act: -0.1700
Data Index: 5033899 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8434. Min Range: -3.8434
Max Act: 3.6244. Min Act: -0.1700
Data Index: 2169160 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19