Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.5102. Min Act: -0.1700
Data Index: 3983207 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.4945. Min Act: -0.1700
Data Index: 5703954 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.3221. Min Act: -0.1700
Data Index: 3655088 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.2907. Min Act: -0.1700
Data Index: 3201983 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.2750. Min Act: -0.1700
Data Index: 5338852 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.2593. Min Act: -0.1700
Data Index: 6846201 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.2436. Min Act: -0.1700
Data Index: 3117507 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.2121. Min Act: -0.1700
Data Index: 6532738 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.2121. Min Act: -0.1700
Data Index: 1112874 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1964. Min Act: -0.1700
Data Index: 829653 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1807. Min Act: -0.1700
Data Index: 4950887 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1807. Min Act: -0.1700
Data Index: 3117513 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1807. Min Act: -0.1700
Data Index: 1968769 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1807. Min Act: -0.1700
Data Index: 4335655 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1492. Min Act: -0.1700
Data Index: 559582 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1335. Min Act: -0.1700
Data Index: 7179670 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1492. Min Act: -0.1700
Data Index: 4512643 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1335. Min Act: -0.1700
Data Index: 3117508 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1177. Min Act: -0.1700
Data Index: 3796697 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5102. Min Range: -3.5102
Max Act: 3.1177. Min Act: -0.1700
Data Index: 2493117 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19