Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0479. Min Range: -6.0479
Max Act: 6.0479. Min Act: -0.1700
Data Index: 4365090 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0479. Min Range: -6.0479
Max Act: 6.0479. Min Act: -0.1700
Data Index: 7022734 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0479. Min Range: -6.0479
Max Act: 6.0479. Min Act: -0.1700
Data Index: 4298618 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2367942 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9854. Min Act: -0.1700
Data Index: 7460270 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9541. Min Act: -0.1700
Data Index: 7898702 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9854. Min Act: -0.1698
Data Index: 4851801 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9541. Min Act: -0.1700
Data Index: 5904645 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9541. Min Act: -0.1700
Data Index: 7894302 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9854. Min Act: -0.1700
Data Index: 3668892 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9229. Min Act: -0.1700
Data Index: 7746715 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9229. Min Act: -0.1700
Data Index: 1127651 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9229. Min Act: -0.1700
Data Index: 8034580 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9541. Min Act: -0.1700
Data Index: 4896974 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9229. Min Act: -0.1700
Data Index: 6140016 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9229. Min Act: -0.1700
Data Index: 1973993 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.8916. Min Act: -0.1700
Data Index: 617691 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.8916. Min Act: -0.1700
Data Index: 445002 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.8916. Min Act: -0.1700
Data Index: 5663068 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0479. Min Range: -6.0479
Max Act: 5.9229. Min Act: -0.1700
Data Index: 3560020 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19