Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5035 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0436. Min Range: -6.0436
Max Act: 6.0436. Min Act: -0.1700
Data Index: 7756011 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.6998. Min Act: -0.1700
Data Index: 2818033 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.6373. Min Act: -0.1700
Data Index: 390862 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.6373. Min Act: -0.1700
Data Index: 7698155 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.6061. Min Act: -0.1700
Data Index: 2818031 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.6061. Min Act: -0.1700
Data Index: 6250359 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.5748. Min Act: -0.1700
Data Index: 7756010 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.5748. Min Act: -0.1700
Data Index: 5103959 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.5436. Min Act: -0.1700
Data Index: 1633440 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.5123. Min Act: -0.1700
Data Index: 6753382 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4811. Min Act: -0.1700
Data Index: 1320395 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4811. Min Act: -0.1700
Data Index: 8617731 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4811. Min Act: -0.1700
Data Index: 2818030 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4811. Min Act: -0.1700
Data Index: 6397966 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4498. Min Act: -0.1700
Data Index: 2818032 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4498. Min Act: -0.1700
Data Index: 2780642 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4498. Min Act: -0.1700
Data Index: 8374988 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4498. Min Act: -0.1700
Data Index: 959802 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.4186. Min Act: -0.1700
Data Index: 5561053 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0436. Min Range: -6.0436
Max Act: 5.3873. Min Act: -0.1700
Data Index: 4360808 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19