Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1018. Min Range: -4.1018
Max Act: 4.1018. Min Act: -0.1700
Data Index: 4696475 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1018. Min Range: -4.1018
Max Act: 4.0081. Min Act: -0.1700
Data Index: 6282088 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.9455. Min Act: -0.1700
Data Index: 5930039 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.9455. Min Act: -0.1700
Data Index: 8269415 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.9143. Min Act: -0.1700
Data Index: 6261232 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.9455. Min Act: -0.1700
Data Index: 5646455 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.9143. Min Act: -0.1700
Data Index: 5860859 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.9455. Min Act: -0.1700
Data Index: 6154492 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8830. Min Act: -0.1700
Data Index: 8246471 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8830. Min Act: -0.1700
Data Index: 3603181 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8830. Min Act: -0.1700
Data Index: 2054747 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8830. Min Act: -0.1700
Data Index: 7566892 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8830. Min Act: -0.1700
Data Index: 4383119 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8517. Min Act: -0.1700
Data Index: 5821924 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8517. Min Act: -0.1700
Data Index: 2863893 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8205. Min Act: -0.1700
Data Index: 6424363 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8517. Min Act: -0.1700
Data Index: 4658830 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8517. Min Act: -0.1700
Data Index: 1825173 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8517. Min Act: -0.1700
Data Index: 3065838 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1018. Min Range: -4.1018
Max Act: 3.8205. Min Act: -0.1700
Data Index: 7747562 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19