Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4602 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0139. Min Range: -8.0139
Max Act: 8.0139. Min Act: -0.1700
Data Index: 3877423 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.5764. Min Act: -0.1700
Data Index: 4682922 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.5139. Min Act: -0.1700
Data Index: 3175758 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.2951. Min Act: -0.1700
Data Index: 1376770 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.2951. Min Act: -0.1700
Data Index: 8219350 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.2639. Min Act: -0.1700
Data Index: 8428551 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.2326. Min Act: -0.1700
Data Index: 6450958 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.1701. Min Act: -0.1700
Data Index: 2642604 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.1701. Min Act: -0.1700
Data Index: 2983655 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.1701. Min Act: -0.1700
Data Index: 216344 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.1389. Min Act: -0.1700
Data Index: 1745390 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.1389. Min Act: -0.1700
Data Index: 861129 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.1076. Min Act: -0.1700
Data Index: 5191757 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.0764. Min Act: -0.1700
Data Index: 5654115 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.0451. Min Act: -0.1700
Data Index: 8567200 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0139. Min Range: -8.0139
Max Act: 7.0139. Min Act: -0.1700
Data Index: 3912507 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0139. Min Range: -8.0139
Max Act: 6.9514. Min Act: -0.1700
Data Index: 5770113 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0139. Min Range: -8.0139
Max Act: 6.9826. Min Act: -0.1700
Data Index: 6042206 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0139. Min Range: -8.0139
Max Act: 6.9514. Min Act: -0.1700
Data Index: 4768334 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0139. Min Range: -8.0139
Max Act: 6.9201. Min Act: -0.1700
Data Index: 1982746 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19