Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1016 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0065. Min Range: -12.0065
Max Act: 12.0065. Min Act: -0.1700
Data Index: 1872574 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0065. Min Range: -12.0065
Max Act: 11.3815. Min Act: -0.1700
Data Index: 4577022 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0065. Min Range: -12.0065
Max Act: 11.3190. Min Act: -0.1700
Data Index: 696592 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0065. Min Range: -12.0065
Max Act: 11.3190. Min Act: -0.1700
Data Index: 4420607 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0065. Min Range: -12.0065
Max Act: 11.1940. Min Act: -0.1700
Data Index: 4759019 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0065. Min Range: -12.0065
Max Act: 11.1940. Min Act: -0.1700
Data Index: 7161383 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0065. Min Range: -12.0065
Max Act: 11.0065. Min Act: -0.1700
Data Index: 1703723 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0065. Min Range: -12.0065
Max Act: 11.0065. Min Act: -0.1700
Data Index: 7438184 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.9440. Min Act: -0.1700
Data Index: 5255070 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.9440. Min Act: -0.1700
Data Index: 2893716 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.8815. Min Act: -0.1700
Data Index: 85897 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.8190. Min Act: -0.1700
Data Index: 7833003 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.7565. Min Act: -0.1700
Data Index: 50421 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.7565. Min Act: -0.1700
Data Index: 2992861 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.6940. Min Act: -0.1700
Data Index: 3819616 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.6940. Min Act: -0.1700
Data Index: 6556305 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.6940. Min Act: -0.1700
Data Index: 5775099 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.6315. Min Act: -0.1700
Data Index: 5396679 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.6315. Min Act: -0.1700
Data Index: 7133222 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0065. Min Range: -12.0065
Max Act: 10.5690. Min Act: -0.1700
Data Index: 5502647 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19