Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.8484. Min Act: -0.1700
Data Index: 605396 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.8484. Min Act: -0.1700
Data Index: 6124480 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.7234. Min Act: -0.1700
Data Index: 6407853 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.6922. Min Act: -0.1700
Data Index: 4624198 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.6922. Min Act: -0.1700
Data Index: 4435628 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.6297. Min Act: -0.1700
Data Index: 112526 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.5672. Min Act: -0.1700
Data Index: 7284656 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.4734. Min Act: -0.1700
Data Index: 1142822 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.4734. Min Act: -0.1700
Data Index: 533397 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.4422. Min Act: -0.1700
Data Index: 7955518 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.4422. Min Act: -0.1700
Data Index: 5433536 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.4109. Min Act: -0.1700
Data Index: 723095 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.3484. Min Act: -0.1700
Data Index: 4436181 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.3797. Min Act: -0.1700
Data Index: 2569323 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.3797. Min Act: -0.1700
Data Index: 1620267 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.3172. Min Act: -0.1700
Data Index: 5333605 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.3172. Min Act: -0.1700
Data Index: 674450 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.3172. Min Act: -0.1700
Data Index: 7395416 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.3172. Min Act: -0.1700
Data Index: 162434 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8484. Min Range: -5.8484
Max Act: 5.2547. Min Act: -0.1700
Data Index: 7350038 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19