Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.9153. Min Act: -0.1700
Data Index: 1597381 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8841. Min Act: -0.1700
Data Index: 1982585 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8841. Min Act: -0.1700
Data Index: 4415487 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8841. Min Act: -0.1700
Data Index: 8555404 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8528. Min Act: -0.1700
Data Index: 3605296 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8841. Min Act: -0.1700
Data Index: 4415500 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8528. Min Act: -0.1700
Data Index: 8555405 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8528. Min Act: -0.1700
Data Index: 1597393 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8216. Min Act: -0.1700
Data Index: 7122764 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8528. Min Act: -0.1700
Data Index: 1597396 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8841. Min Act: -0.1700
Data Index: 5158114 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8216. Min Act: -0.1700
Data Index: 4349439 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8216. Min Act: -0.1700
Data Index: 5158117 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8216. Min Act: -0.1700
Data Index: 4599564 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.8216. Min Act: -0.1700
Data Index: 1606636 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.7903. Min Act: -0.1700
Data Index: 5056214 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.7591. Min Act: -0.1700
Data Index: 2296693 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.7903. Min Act: -0.1700
Data Index: 3378122 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.7903. Min Act: -0.1700
Data Index: 4599575 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9153. Min Range: -4.9153
Max Act: 4.7903. Min Act: -0.1700
Data Index: 2296704 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19