Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0065. Min Range: -5.0065
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4879794 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.9752. Min Act: -0.1700
Data Index: 1248557 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.9440. Min Act: -0.1700
Data Index: 4542833 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.7877. Min Act: -0.1700
Data Index: 4915488 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.7877. Min Act: -0.1700
Data Index: 1534467 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.7877. Min Act: -0.1700
Data Index: 3933515 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.7252. Min Act: -0.1700
Data Index: 7757823 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.6002. Min Act: -0.1700
Data Index: 348852 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.6315. Min Act: -0.1700
Data Index: 8359111 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.6315. Min Act: -0.1700
Data Index: 5608210 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.6315. Min Act: -0.1700
Data Index: 6768609 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.5690. Min Act: -0.1700
Data Index: 633963 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.6002. Min Act: -0.1700
Data Index: 322480 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.5690. Min Act: -0.1700
Data Index: 4868774 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.5377. Min Act: -0.1700
Data Index: 3326871 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.5690. Min Act: -0.1700
Data Index: 694798 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.6002. Min Act: -0.1700
Data Index: 7757859 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.5690. Min Act: -0.1700
Data Index: 7488020 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.5690. Min Act: -0.1700
Data Index: 6245891 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0065. Min Range: -5.0065
Max Act: 4.5377. Min Act: -0.1700
Data Index: 2835747 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19