Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.3578. Min Act: -0.1700
Data Index: 8553452 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.2328. Min Act: -0.1700
Data Index: 2578741 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.2641. Min Act: -0.1700
Data Index: 150050 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.2641. Min Act: -0.1700
Data Index: 428404 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.1703. Min Act: -0.1700
Data Index: 106030 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.1391. Min Act: -0.1700
Data Index: 3647693 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.1703. Min Act: -0.1700
Data Index: 1296832 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.1703. Min Act: -0.1700
Data Index: 2466015 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.0453. Min Act: -0.1700
Data Index: 5793224 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.0453. Min Act: -0.1700
Data Index: 1108324 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3578. Min Range: -7.3578
Max Act: 6.9828. Min Act: -0.1700
Data Index: 6771294 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.0141. Min Act: -0.1700
Data Index: 3414559 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.0141. Min Act: -0.1700
Data Index: 245150 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3578. Min Range: -7.3578
Max Act: 7.0141. Min Act: -0.1700
Data Index: 5961185 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3578. Min Range: -7.3578
Max Act: 6.9828. Min Act: -0.1700
Data Index: 6106604 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3578. Min Range: -7.3578
Max Act: 6.9828. Min Act: -0.1700
Data Index: 604972 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3578. Min Range: -7.3578
Max Act: 6.9828. Min Act: -0.1700
Data Index: 7045379 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3578. Min Range: -7.3578
Max Act: 6.9828. Min Act: -0.1700
Data Index: 5779486 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3578. Min Range: -7.3578
Max Act: 6.9516. Min Act: -0.1700
Data Index: 6081840 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3578. Min Range: -7.3578
Max Act: 6.9203. Min Act: -0.1700
Data Index: 2181039 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19