Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1595 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.1187. Min Range: -11.1187
Max Act: 11.1187. Min Act: -0.1700
Data Index: 8656299 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1187. Min Range: -11.1187
Max Act: 10.1812. Min Act: -0.1700
Data Index: 8226466 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.9937. Min Act: -0.1700
Data Index: 1776101 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.8687. Min Act: -0.1700
Data Index: 5854632 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.6812. Min Act: -0.1700
Data Index: 8693047 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.5562. Min Act: -0.1700
Data Index: 7634360 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.5562. Min Act: -0.1700
Data Index: 4018358 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.5562. Min Act: -0.1700
Data Index: 898010 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.4937. Min Act: -0.1700
Data Index: 7589966 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.6187. Min Act: -0.1700
Data Index: 1052197 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.5562. Min Act: -0.1700
Data Index: 2710477 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.4312. Min Act: -0.1700
Data Index: 8719607 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.4937. Min Act: -0.1700
Data Index: 8706277 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.3687. Min Act: -0.1700
Data Index: 485255 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.3687. Min Act: -0.1700
Data Index: 467669 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.2437. Min Act: -0.1700
Data Index: 7713845 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.3062. Min Act: -0.1700
Data Index: 777294 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.3062. Min Act: -0.1700
Data Index: 4385980 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.2437. Min Act: -0.1700
Data Index: 6384399 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1187. Min Range: -11.1187
Max Act: 9.2437. Min Act: -0.1700
Data Index: 2411330 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19