Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.6758. Min Act: -0.1700
Data Index: 3156548 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.6914. Min Act: -0.1700
Data Index: 5328824 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.6289. Min Act: -0.1700
Data Index: 3561021 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.5976. Min Act: -0.1700
Data Index: 3221550 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.5819. Min Act: -0.1700
Data Index: 3277453 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.5349. Min Act: -0.1700
Data Index: 4676246 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.5036. Min Act: -0.1700
Data Index: 7661032 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.5193. Min Act: -0.1700
Data Index: 6524316 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.5349. Min Act: -0.1700
Data Index: 7050625 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4880. Min Act: -0.1700
Data Index: 950743 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4723. Min Act: -0.1700
Data Index: 268723 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4880. Min Act: -0.1700
Data Index: 6145331 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4723. Min Act: -0.1700
Data Index: 1403537 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4566. Min Act: -0.1700
Data Index: 993801 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4410. Min Act: -0.1700
Data Index: 5684843 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4410. Min Act: -0.1700
Data Index: 6946157 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4410. Min Act: -0.1700
Data Index: 6850618 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4410. Min Act: -0.1700
Data Index: 4612619 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4253. Min Act: -0.1700
Data Index: 2332033 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6914. Min Range: -3.6914
Max Act: 3.4253. Min Act: -0.1700
Data Index: 3566937 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19