Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.6515. Min Act: -0.1700
Data Index: 368819 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.6203. Min Act: -0.1700
Data Index: 368820 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.3703. Min Act: -0.1700
Data Index: 1717770 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.3078. Min Act: -0.1700
Data Index: 3485209 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.3078. Min Act: -0.1700
Data Index: 744490 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.2765. Min Act: -0.1700
Data Index: 8017074 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.1828. Min Act: -0.1700
Data Index: 5845664 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.1828. Min Act: -0.1700
Data Index: 3024409 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.1828. Min Act: -0.1700
Data Index: 434902 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.1515. Min Act: -0.1700
Data Index: 6300067 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0890. Min Act: -0.1700
Data Index: 434900 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0578. Min Act: -0.1700
Data Index: 3654544 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0578. Min Act: -0.1700
Data Index: 6797487 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0890. Min Act: -0.1700
Data Index: 5202949 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0578. Min Act: -0.1700
Data Index: 1941148 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0578. Min Act: -0.1700
Data Index: 6479214 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 6689539 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 434901 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 406091 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6515. Min Range: -5.6515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 3626786 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19