Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.7988. Min Act: -0.1700
Data Index: 871586 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.7363. Min Act: -0.1700
Data Index: 4955133 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.7363. Min Act: -0.1700
Data Index: 8517048 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.7051. Min Act: -0.1700
Data Index: 5969245 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.6426. Min Act: -0.1700
Data Index: 4497346 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.6426. Min Act: -0.1700
Data Index: 4617193 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.6426. Min Act: -0.1700
Data Index: 320309 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.5488. Min Act: -0.1700
Data Index: 333515 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.5488. Min Act: -0.1700
Data Index: 8224131 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.5488. Min Act: -0.1700
Data Index: 2670457 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.5488. Min Act: -0.1700
Data Index: 6026068 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1819015 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1379636 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.4863. Min Act: -0.1700
Data Index: 4874278 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.4863. Min Act: -0.1700
Data Index: 4643106 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7730255 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.4551. Min Act: -0.1700
Data Index: 2276782 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7313385 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.4551. Min Act: -0.1700
Data Index: 6657445 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7988. Min Range: -5.7988
Max Act: 5.4551. Min Act: -0.1700
Data Index: 4150282 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19