Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.5774. Min Act: -0.1700
Data Index: 1730020 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.5462. Min Act: -0.1700
Data Index: 6972123 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.5149. Min Act: -0.1700
Data Index: 3874480 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.5149. Min Act: -0.1700
Data Index: 1931665 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.4837. Min Act: -0.1700
Data Index: 1341953 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.3587. Min Act: -0.1700
Data Index: 7699889 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.3587. Min Act: -0.1700
Data Index: 7820113 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.3274. Min Act: -0.1700
Data Index: 7638703 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.3274. Min Act: -0.1700
Data Index: 1385193 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.2649. Min Act: -0.1700
Data Index: 6278104 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.2649. Min Act: -0.1700
Data Index: 6510963 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.2649. Min Act: -0.1700
Data Index: 1713536 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.2337. Min Act: -0.1700
Data Index: 4512086 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.1712. Min Act: -0.1700
Data Index: 805578 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.2024. Min Act: -0.1700
Data Index: 466193 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.2024. Min Act: -0.1700
Data Index: 456602 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.2024. Min Act: -0.1700
Data Index: 2670750 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.1712. Min Act: -0.1700
Data Index: 4702524 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.1712. Min Act: -0.1700
Data Index: 538214 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5774. Min Range: -5.5774
Max Act: 5.1399. Min Act: -0.1700
Data Index: 1435279 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19