Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.5995. Min Act: -0.1700
Data Index: 8260232 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.5369. Min Act: -0.1700
Data Index: 3439042 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.5369. Min Act: -0.1700
Data Index: 6848730 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.4744. Min Act: -0.1700
Data Index: 3250038 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.4119. Min Act: -0.1700
Data Index: 259103 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.4119. Min Act: -0.1700
Data Index: 2220735 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3807. Min Act: -0.1700
Data Index: 833229 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3807. Min Act: -0.1700
Data Index: 8703668 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3807. Min Act: -0.1700
Data Index: 6358786 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5912346 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3807. Min Act: -0.1700
Data Index: 5527054 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3494. Min Act: -0.1700
Data Index: 3590642 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3494. Min Act: -0.1700
Data Index: 1995089 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3494. Min Act: -0.1700
Data Index: 6991883 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3807. Min Act: -0.1700
Data Index: 4241049 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3182. Min Act: -0.1700
Data Index: 8115389 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3494. Min Act: -0.1700
Data Index: 2611501 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3182. Min Act: -0.1700
Data Index: 8799983 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.3182. Min Act: -0.1700
Data Index: 261874 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5995. Min Range: -4.5995
Max Act: 4.2869. Min Act: -0.1700
Data Index: 829690 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19