Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.9522. Min Act: -0.1700
Data Index: 4367380 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.8897. Min Act: -0.1700
Data Index: 4007100 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.7334. Min Act: -0.1700
Data Index: 5293870 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.6709. Min Act: -0.1700
Data Index: 3855336 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.6397. Min Act: -0.1700
Data Index: 967415 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.6084. Min Act: -0.1700
Data Index: 8267041 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.6084. Min Act: -0.1700
Data Index: 3216207 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.6084. Min Act: -0.1700
Data Index: 4001265 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.5772. Min Act: -0.1700
Data Index: 6633891 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.5459. Min Act: -0.1700
Data Index: 4538108 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.5459. Min Act: -0.1700
Data Index: 4554020 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.5147. Min Act: -0.1700
Data Index: 8582499 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.4834. Min Act: -0.1700
Data Index: 968434 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.4834. Min Act: -0.1700
Data Index: 7120859 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.4834. Min Act: -0.1700
Data Index: 214374 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.4834. Min Act: -0.1700
Data Index: 8709866 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.4522. Min Act: -0.1700
Data Index: 7897734 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.4209. Min Act: -0.1700
Data Index: 6562737 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.4209. Min Act: -0.1700
Data Index: 253204 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9522. Min Range: -5.9522
Max Act: 5.3897. Min Act: -0.1700
Data Index: 8050574 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19