Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.9891. Min Act: -0.1700
Data Index: 2537344 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.9266. Min Act: -0.1700
Data Index: 644861 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.9266. Min Act: -0.1700
Data Index: 3661618 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7849580 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.8641. Min Act: -0.1700
Data Index: 4216989 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.8641. Min Act: -0.1700
Data Index: 816140 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.8016. Min Act: -0.1700
Data Index: 644863 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.8016. Min Act: -0.1700
Data Index: 2190849 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.7703. Min Act: -0.1700
Data Index: 3250817 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.7391. Min Act: -0.1700
Data Index: 5297144 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.7391. Min Act: -0.1700
Data Index: 5456067 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.7391. Min Act: -0.1700
Data Index: 2997314 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.7078. Min Act: -0.1700
Data Index: 3690683 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.7078. Min Act: -0.1700
Data Index: 1598945 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.6766. Min Act: -0.1700
Data Index: 7208730 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.6766. Min Act: -0.1700
Data Index: 1671397 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.6766. Min Act: -0.1700
Data Index: 2371086 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.6766. Min Act: -0.1700
Data Index: 6222904 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.6453. Min Act: -0.1700
Data Index: 1207174 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9891. Min Range: -4.9891
Max Act: 4.6141. Min Act: -0.1700
Data Index: 2295958 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19