Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2609 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.6906. Min Act: -0.1700
Data Index: 2797352 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.6593. Min Act: -0.1700
Data Index: 569468 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.6281. Min Act: -0.1700
Data Index: 610825 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.6281. Min Act: -0.1700
Data Index: 1542892 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.6281. Min Act: -0.1700
Data Index: 8018978 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.5968. Min Act: -0.1700
Data Index: 7309160 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.5343. Min Act: -0.1700
Data Index: 2976041 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.5031. Min Act: -0.1700
Data Index: 5004468 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4406. Min Act: -0.1700
Data Index: 6704736 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4718. Min Act: -0.1700
Data Index: 4242852 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4718. Min Act: -0.1700
Data Index: 7911900 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4406. Min Act: -0.1700
Data Index: 3671226 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4406. Min Act: -0.1700
Data Index: 4162799 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4406. Min Act: -0.1700
Data Index: 2204171 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4093. Min Act: -0.1700
Data Index: 5743166 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4093. Min Act: -0.1700
Data Index: 2849008 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4093. Min Act: -0.1700
Data Index: 8718329 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.4093. Min Act: -0.1700
Data Index: 5890257 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.3781. Min Act: -0.1700
Data Index: 5833768 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6906. Min Range: -5.6906
Max Act: 5.3781. Min Act: -0.1700
Data Index: 5676098 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19