Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1691 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.7706. Min Act: -0.1700
Data Index: 4546145 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.7394. Min Act: -0.1700
Data Index: 3572724 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.7081. Min Act: -0.1700
Data Index: 5623997 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.6144. Min Act: -0.1700
Data Index: 6563128 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.5831. Min Act: -0.1700
Data Index: 3221216 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.5519. Min Act: -0.1700
Data Index: 1022393 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.5519. Min Act: -0.1700
Data Index: 2654842 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.5831. Min Act: -0.1700
Data Index: 5022178 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.5519. Min Act: -0.1700
Data Index: 7511727 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.5206. Min Act: -0.1700
Data Index: 2733878 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.4581. Min Act: -0.1700
Data Index: 6527221 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.4581. Min Act: -0.1700
Data Index: 4562110 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.4269. Min Act: -0.1700
Data Index: 6271205 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.4269. Min Act: -0.1700
Data Index: 307956 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.3956. Min Act: -0.1700
Data Index: 3927712 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.3956. Min Act: -0.1700
Data Index: 5599032 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.3644. Min Act: -0.1700
Data Index: 1964810 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.3331. Min Act: -0.1700
Data Index: 1006520 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.3019. Min Act: -0.1700
Data Index: 6594876 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7706. Min Range: -7.7706
Max Act: 7.2706. Min Act: -0.1700
Data Index: 133587 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19