Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5236 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.7517. Min Act: -0.1700
Data Index: 7217596 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.6735. Min Act: -0.1700
Data Index: 3712559 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.6422. Min Act: -0.1700
Data Index: 8000218 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.6109. Min Act: -0.1700
Data Index: 6808732 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5952. Min Act: -0.1700
Data Index: 55217 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5639. Min Act: -0.1700
Data Index: 1595447 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5326. Min Act: -0.1700
Data Index: 3979347 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5483. Min Act: -0.1700
Data Index: 907056 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5483. Min Act: -0.1700
Data Index: 2826396 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5326. Min Act: -0.1700
Data Index: 3751390 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5326. Min Act: -0.1700
Data Index: 7315876 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.5013. Min Act: -0.1700
Data Index: 1709469 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4699. Min Act: -0.1700
Data Index: 8192018 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4699. Min Act: -0.1700
Data Index: 6638442 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4699. Min Act: -0.1700
Data Index: 8028380 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4699. Min Act: -0.1700
Data Index: 3545702 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4543. Min Act: -0.1700
Data Index: 212572 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4543. Min Act: -0.1700
Data Index: 2253060 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4699. Min Act: -0.1700
Data Index: 6217506 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7517. Min Range: -3.7517
Max Act: 3.4543. Min Act: -0.1700
Data Index: 5459013 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19