Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.7694. Min Act: -0.1700
Data Index: 5781235 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.5819. Min Act: -0.1700
Data Index: 5657055 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.5819. Min Act: -0.1700
Data Index: 7323615 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.5194. Min Act: -0.1700
Data Index: 3012002 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.4881. Min Act: -0.1700
Data Index: 3554299 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.4569. Min Act: -0.1700
Data Index: 3036756 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.4256. Min Act: -0.1700
Data Index: 5505450 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.3944. Min Act: -0.1700
Data Index: 2452776 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.3631. Min Act: -0.1700
Data Index: 8074965 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.3006. Min Act: -0.1700
Data Index: 4616771 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.2694. Min Act: -0.1700
Data Index: 6316181 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.3006. Min Act: -0.1700
Data Index: 5104082 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.3006. Min Act: -0.1700
Data Index: 5381313 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.3006. Min Act: -0.1700
Data Index: 5162807 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.2694. Min Act: -0.1700
Data Index: 8546122 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.2694. Min Act: -0.1700
Data Index: 3949211 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.2694. Min Act: -0.1700
Data Index: 7921399 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.2694. Min Act: -0.1700
Data Index: 353478 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.2694. Min Act: -0.1700
Data Index: 6607580 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7694. Min Range: -4.7694
Max Act: 4.2694. Min Act: -0.1700
Data Index: 5815251 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19