Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4507 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2327. Min Range: -10.2327
Max Act: 10.2327. Min Act: -0.1700
Data Index: 1618686 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2327. Min Range: -10.2327
Max Act: 10.0452. Min Act: -0.1700
Data Index: 4591755 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2327. Min Range: -10.2327
Max Act: 10.0452. Min Act: -0.1700
Data Index: 7049444 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.9202. Min Act: -0.1700
Data Index: 7799603 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.9827. Min Act: -0.1700
Data Index: 8092534 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.9202. Min Act: -0.1700
Data Index: 4879044 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.9202. Min Act: -0.1700
Data Index: 7295215 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.9827. Min Act: -0.1700
Data Index: 7744239 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.7952. Min Act: -0.1700
Data Index: 8328104 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.7327. Min Act: -0.1700
Data Index: 8480537 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.7327. Min Act: -0.1700
Data Index: 3905960 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6702. Min Act: -0.1700
Data Index: 7444658 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6702. Min Act: -0.1700
Data Index: 8243240 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6077. Min Act: -0.1700
Data Index: 4161682 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6077. Min Act: -0.1700
Data Index: 411479 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6077. Min Act: -0.1700
Data Index: 6250391 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6077. Min Act: -0.1700
Data Index: 4902244 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6077. Min Act: -0.1700
Data Index: 6113133 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6077. Min Act: -0.1700
Data Index: 8311607 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2327. Min Range: -10.2327
Max Act: 9.6077. Min Act: -0.1700
Data Index: 5605136 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19