Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.7262. Min Act: -0.1700
Data Index: 7698568 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.5074. Min Act: -0.1700
Data Index: 690022 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.4137. Min Act: -0.1700
Data Index: 966578 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.3824. Min Act: -0.1700
Data Index: 4393981 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.3199. Min Act: -0.1700
Data Index: 1877149 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.3199. Min Act: -0.1700
Data Index: 1683877 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.2262. Min Act: -0.1700
Data Index: 8117130 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.2262. Min Act: -0.1700
Data Index: 8726825 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1949. Min Act: -0.1700
Data Index: 1062075 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1949. Min Act: -0.1700
Data Index: 5896840 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.2262. Min Act: -0.1700
Data Index: 4658994 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1949. Min Act: -0.1700
Data Index: 6949356 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1637. Min Act: -0.1700
Data Index: 4959684 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1637. Min Act: -0.1700
Data Index: 8500560 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1637. Min Act: -0.1700
Data Index: 3866245 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1012. Min Act: -0.1700
Data Index: 1647871 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1637. Min Act: -0.1700
Data Index: 4752227 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1012. Min Act: -0.1700
Data Index: 7544739 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1324. Min Act: -0.1700
Data Index: 631203 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7262. Min Range: -6.7262
Max Act: 6.1012. Min Act: -0.1700
Data Index: 5658731 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19