Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1732 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1757. Min Range: -7.1757
Max Act: 7.1757. Min Act: -0.1700
Data Index: 7492727 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1757. Min Range: -7.1757
Max Act: 7.1444. Min Act: -0.1700
Data Index: 2829596 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.8632. Min Act: -0.1700
Data Index: 3063572 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.8007. Min Act: -0.1700
Data Index: 7299279 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6132. Min Act: -0.1700
Data Index: 2934403 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6444. Min Act: -0.1700
Data Index: 1779077 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6132. Min Act: -0.1700
Data Index: 414544 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6132. Min Act: -0.1700
Data Index: 3283037 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5819. Min Act: -0.1700
Data Index: 531547 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5819. Min Act: -0.1700
Data Index: 6543428 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5507. Min Act: -0.1700
Data Index: 1907671 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5507. Min Act: -0.1700
Data Index: 605634 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5507. Min Act: -0.1700
Data Index: 356213 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5194. Min Act: -0.1700
Data Index: 652789 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.4882. Min Act: -0.1700
Data Index: 2985019 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5194. Min Act: -0.1700
Data Index: 4310281 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.4569. Min Act: -0.1700
Data Index: 3274175 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.4569. Min Act: -0.1700
Data Index: 8271569 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.4882. Min Act: -0.1700
Data Index: 2776169 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.4569. Min Act: -0.1700
Data Index: 5605245 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19