Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1533 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.5436. Min Act: -0.1700
Data Index: 7586271 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.5123. Min Act: -0.1699
Data Index: 3172647 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.4811. Min Act: -0.1700
Data Index: 1797829 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.4498. Min Act: -0.1700
Data Index: 7250878 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.3873. Min Act: -0.1700
Data Index: 7718263 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.4186. Min Act: -0.1700
Data Index: 4776948 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.3873. Min Act: -0.1700
Data Index: 5700473 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.3873. Min Act: -0.1700
Data Index: 565700 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.3561. Min Act: -0.1700
Data Index: 7081855 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.3561. Min Act: -0.1700
Data Index: 4525224 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.3248. Min Act: -0.1700
Data Index: 126894 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.2623. Min Act: -0.1700
Data Index: 7278446 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.2623. Min Act: -0.1700
Data Index: 702869 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.2623. Min Act: -0.1700
Data Index: 2573529 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.2936. Min Act: -0.1700
Data Index: 4400119 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.2311. Min Act: -0.1700
Data Index: 1251227 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.2311. Min Act: -0.1700
Data Index: 256626 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.1998. Min Act: -0.1700
Data Index: 1994354 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.1998. Min Act: -0.1700
Data Index: 8154077 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5436. Min Range: -6.5436
Max Act: 6.1686. Min Act: -0.1700
Data Index: 6996506 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19