Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3201 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.7982. Min Act: -0.1700
Data Index: 4179677 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.7670. Min Act: -0.1700
Data Index: 5532922 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.6420. Min Act: -0.1700
Data Index: 8716133 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.6107. Min Act: -0.1700
Data Index: 3286961 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.5795. Min Act: -0.1700
Data Index: 1903081 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.5170. Min Act: -0.1700
Data Index: 3291217 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4857. Min Act: -0.1700
Data Index: 991147 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4857. Min Act: -0.1700
Data Index: 8098113 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4545. Min Act: -0.1700
Data Index: 6933339 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4545. Min Act: -0.1700
Data Index: 6691332 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4545. Min Act: -0.1700
Data Index: 1474650 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4545. Min Act: -0.1700
Data Index: 2458305 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4232. Min Act: -0.1700
Data Index: 4753716 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4232. Min Act: -0.1700
Data Index: 3927674 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4232. Min Act: -0.1700
Data Index: 1367968 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4545. Min Act: -0.1700
Data Index: 5958192 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.3920. Min Act: -0.1700
Data Index: 7195781 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.3920. Min Act: -0.1700
Data Index: 6594694 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.4232. Min Act: -0.1700
Data Index: 4256663 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7982. Min Range: -5.7982
Max Act: 5.3920. Min Act: -0.1700
Data Index: 4604879 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19