Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.9321. Min Act: -0.1700
Data Index: 492477 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.8696. Min Act: -0.1700
Data Index: 888326 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.8383. Min Act: -0.1700
Data Index: 8515363 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7914. Min Act: -0.1700
Data Index: 3944415 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7914. Min Act: -0.1700
Data Index: 7055255 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7445. Min Act: -0.1700
Data Index: 6758499 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7601. Min Act: -0.1700
Data Index: 2329181 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7445. Min Act: -0.1700
Data Index: 1084100 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7445. Min Act: -0.1700
Data Index: 1004925 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7288. Min Act: -0.1700
Data Index: 5847565 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7288. Min Act: -0.1700
Data Index: 3099743 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7132. Min Act: -0.1700
Data Index: 930001 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7288. Min Act: -0.1700
Data Index: 6590803 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7132. Min Act: -0.1700
Data Index: 7187672 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7132. Min Act: -0.1700
Data Index: 4565245 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.7132. Min Act: -0.1700
Data Index: 7393454 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.6976. Min Act: -0.1700
Data Index: 4605107 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.6976. Min Act: -0.1700
Data Index: 2166169 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.6663. Min Act: -0.1700
Data Index: 4472500 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9321. Min Range: -3.9321
Max Act: 3.6663. Min Act: -0.1700
Data Index: 116388 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19