Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0621. Min Range: -3.0621
Max Act: 3.0621. Min Act: -0.1700
Data Index: 2792987 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.9831. Min Act: -0.1700
Data Index: 656637 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.9515. Min Act: -0.1700
Data Index: 4594800 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.9673. Min Act: -0.1700
Data Index: 170953 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.9356. Min Act: -0.1700
Data Index: 7979394 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.9356. Min Act: -0.1700
Data Index: 979942 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.9198. Min Act: -0.1700
Data Index: 319926 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8881. Min Act: -0.1700
Data Index: 3457742 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8722. Min Act: -0.1700
Data Index: 5446100 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8722. Min Act: -0.1700
Data Index: 4134102 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8722. Min Act: -0.1700
Data Index: 209613 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8722. Min Act: -0.1700
Data Index: 5839625 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8563. Min Act: -0.1700
Data Index: 5724406 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8563. Min Act: -0.1700
Data Index: 3909428 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8563. Min Act: -0.1700
Data Index: 1354977 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8563. Min Act: -0.1700
Data Index: 4439814 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8404. Min Act: -0.1700
Data Index: 2214318 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8404. Min Act: -0.1700
Data Index: 1141876 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8404. Min Act: -0.1700
Data Index: 4267686 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0621. Min Range: -3.0621
Max Act: 2.8404. Min Act: -0.1700
Data Index: 2688769 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19