Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0481. Min Range: -5.0481
Max Act: 5.0481. Min Act: -0.1700
Data Index: 64875 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.9856. Min Act: -0.1700
Data Index: 2282451 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.9231. Min Act: -0.1700
Data Index: 64876 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8919. Min Act: -0.1700
Data Index: 1460885 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8606. Min Act: -0.1700
Data Index: 4622277 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8606. Min Act: -0.1700
Data Index: 345978 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8919. Min Act: -0.1700
Data Index: 2282448 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8294. Min Act: -0.1700
Data Index: 3157416 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8294. Min Act: -0.1700
Data Index: 3742179 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8606. Min Act: -0.1700
Data Index: 4170399 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7981. Min Act: -0.1700
Data Index: 4659432 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7981. Min Act: -0.1700
Data Index: 4296650 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.8294. Min Act: -0.1700
Data Index: 6407948 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7669. Min Act: -0.1700
Data Index: 961831 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7356. Min Act: -0.1700
Data Index: 3258355 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7669. Min Act: -0.1700
Data Index: 1371553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7669. Min Act: -0.1700
Data Index: 4768310 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7669. Min Act: -0.1700
Data Index: 204847 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7669. Min Act: -0.1700
Data Index: 2794571 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0481. Min Range: -5.0481
Max Act: 4.7669. Min Act: -0.1700
Data Index: 3871422 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19