Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4120 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.5564. Min Act: -0.1700
Data Index: 4892097 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.4314. Min Act: -0.1700
Data Index: 2606503 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.2439. Min Act: -0.1700
Data Index: 1367767 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.2126. Min Act: -0.1700
Data Index: 5987011 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.1814. Min Act: -0.1700
Data Index: 4456979 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.1814. Min Act: -0.1700
Data Index: 2286136 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.1814. Min Act: -0.1700
Data Index: 4164958 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.1501. Min Act: -0.1700
Data Index: 4889780 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6198331 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.0876. Min Act: -0.1700
Data Index: 4456988 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5564. Min Range: -5.5564
Max Act: 5.0876. Min Act: -0.1700
Data Index: 2439806 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.9939. Min Act: -0.1700
Data Index: 8231079 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.9939. Min Act: -0.1700
Data Index: 5783234 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.9626. Min Act: -0.1700
Data Index: 6344039 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.9314. Min Act: -0.1700
Data Index: 4943181 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.8689. Min Act: -0.1700
Data Index: 1416269 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.8376. Min Act: -0.1700
Data Index: 2766999 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.7751. Min Act: -0.1700
Data Index: 4767859 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.8064. Min Act: -0.1700
Data Index: 7355112 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5564. Min Range: -5.5564
Max Act: 4.7751. Min Act: -0.1700
Data Index: 1918342 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19