Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 916 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.7454. Min Act: -0.1700
Data Index: 8069060 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.7141. Min Act: -0.1700
Data Index: 5118379 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.7141. Min Act: -0.1700
Data Index: 7931409 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 990877 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.7141. Min Act: -0.1700
Data Index: 5554926 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.7141. Min Act: -0.1700
Data Index: 3761079 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 4209710 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 7611671 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 748085 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 794955 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 4420732 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 3699414 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 7337281 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 3452491 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6516. Min Act: -0.1700
Data Index: 3046697 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 2492933 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 1347541 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 3029127 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.5891. Min Act: -0.1700
Data Index: 1428675 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7454. Min Range: -5.7454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 2210810 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19