Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6106 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.7045. Min Act: -0.1700
Data Index: 7007841 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.3608. Min Act: -0.1700
Data Index: 7664963 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.3608. Min Act: -0.1700
Data Index: 5104093 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.2983. Min Act: -0.1700
Data Index: 3805843 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.2670. Min Act: -0.1700
Data Index: 463550 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.2358. Min Act: -0.1700
Data Index: 1055360 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.2045. Min Act: -0.1700
Data Index: 3902462 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.1108. Min Act: -0.1700
Data Index: 2764858 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.1108. Min Act: -0.1700
Data Index: 6342636 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.0483. Min Act: -0.1700
Data Index: 1820744 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.0170. Min Act: -0.1700
Data Index: 3778459 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7045. Min Range: -6.7045
Max Act: 6.0170. Min Act: -0.1700
Data Index: 2881220 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9858. Min Act: -0.1700
Data Index: 5616051 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9858. Min Act: -0.1700
Data Index: 6186713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9858. Min Act: -0.1700
Data Index: 5042267 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9858. Min Act: -0.1700
Data Index: 184887 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9858. Min Act: -0.1700
Data Index: 8098830 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9545. Min Act: -0.1700
Data Index: 4327362 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9545. Min Act: -0.1700
Data Index: 4041609 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7045. Min Range: -6.7045
Max Act: 5.9858. Min Act: -0.1700
Data Index: 1401908 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19