Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.9974. Min Act: -0.1700
Data Index: 7901518 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.8411. Min Act: -0.1700
Data Index: 1604669 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.6849. Min Act: -0.1699
Data Index: 2469533 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.6849. Min Act: -0.1700
Data Index: 1243995 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.6849. Min Act: -0.1700
Data Index: 4979022 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.6536. Min Act: -0.1700
Data Index: 326723 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.6536. Min Act: -0.1700
Data Index: 5512982 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.6536. Min Act: -0.1700
Data Index: 1441240 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.6224. Min Act: -0.1700
Data Index: 6538448 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5911. Min Act: -0.1699
Data Index: 4379848 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5599. Min Act: -0.1700
Data Index: 4215247 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5286. Min Act: -0.1677
Data Index: 2626582 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5599. Min Act: -0.1700
Data Index: 5839011 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5599. Min Act: -0.1700
Data Index: 365609 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5286. Min Act: -0.1700
Data Index: 446702 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5599. Min Act: -0.1700
Data Index: 8781421 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5599. Min Act: -0.1699
Data Index: 1587354 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5286. Min Act: -0.1700
Data Index: 4920177 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5286. Min Act: -0.1700
Data Index: 4842265 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9974. Min Range: -5.9974
Max Act: 5.5286. Min Act: -0.1700
Data Index: 4379850 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19