Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5008 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4016. Min Range: -8.4016
Max Act: 8.4016. Min Act: -0.1700
Data Index: 7075248 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4016. Min Range: -8.4016
Max Act: 8.2766. Min Act: -0.1699
Data Index: 5177501 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4016. Min Range: -8.4016
Max Act: 8.1516. Min Act: -0.1700
Data Index: 2393374 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.9016. Min Act: -0.1700
Data Index: 2703451 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.8391. Min Act: -0.1700
Data Index: 7435053 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.6829. Min Act: -0.1700
Data Index: 6025506 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.6516. Min Act: -0.1700
Data Index: 5177500 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.6516. Min Act: -0.1700
Data Index: 5355610 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.5579. Min Act: -0.1700
Data Index: 3878306 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.5579. Min Act: -0.1700
Data Index: 236710 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.5266. Min Act: -0.1700
Data Index: 2211268 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.4954. Min Act: -0.1700
Data Index: 7475825 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.4329. Min Act: -0.1700
Data Index: 4234764 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3704. Min Act: -0.1700
Data Index: 5177499 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3391. Min Act: -0.1700
Data Index: 2703444 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3704. Min Act: -0.1700
Data Index: 7360056 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3704. Min Act: -0.1700
Data Index: 3758016 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3704. Min Act: -0.1700
Data Index: 884402 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3391. Min Act: -0.1700
Data Index: 5203669 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4016. Min Range: -8.4016
Max Act: 7.3391. Min Act: -0.1700
Data Index: 7415200 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19