Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6987. Min Range: -12.6987
Max Act: 12.6987. Min Act: -0.1700
Data Index: 584220 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6987. Min Range: -12.6987
Max Act: 12.5112. Min Act: -0.1700
Data Index: 4716260 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6987. Min Range: -12.6987
Max Act: 12.1362. Min Act: -0.1700
Data Index: 5179018 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6987. Min Range: -12.6987
Max Act: 12.0112. Min Act: -0.1700
Data Index: 2144988 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.9487. Min Act: -0.1700
Data Index: 2298957 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.9487. Min Act: -0.1700
Data Index: 3002628 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6987. Min Range: -12.6987
Max Act: 12.0112. Min Act: -0.1700
Data Index: 7597788 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.8237. Min Act: -0.1700
Data Index: 7828457 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.7612. Min Act: -0.1700
Data Index: 4329207 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.8237. Min Act: -0.1700
Data Index: 2320696 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.8237. Min Act: -0.1700
Data Index: 8221386 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.7612. Min Act: -0.1700
Data Index: 8627591 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.6987. Min Act: -0.1700
Data Index: 1523912 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.6987. Min Act: -0.1700
Data Index: 1160598 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.6362. Min Act: -0.1700
Data Index: 4438845 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.6362. Min Act: -0.1700
Data Index: 8658281 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.5737. Min Act: -0.1700
Data Index: 8651622 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.5737. Min Act: -0.1700
Data Index: 4530901 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.5112. Min Act: -0.1700
Data Index: 2203789 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6987. Min Range: -12.6987
Max Act: 11.5737. Min Act: -0.1700
Data Index: 638294 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19