Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.9019. Min Act: -0.1700
Data Index: 8063996 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.4956. Min Act: -0.1700
Data Index: 1895997 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.4956. Min Act: -0.1700
Data Index: 5370900 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.4956. Min Act: -0.1700
Data Index: 714210 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.4956. Min Act: -0.1700
Data Index: 1214462 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.4019. Min Act: -0.1700
Data Index: 8129473 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.3706. Min Act: -0.1700
Data Index: 489553 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.3706. Min Act: -0.1700
Data Index: 887425 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.2456. Min Act: -0.1700
Data Index: 6402391 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.2144. Min Act: -0.1700
Data Index: 2928541 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.1831. Min Act: -0.1700
Data Index: 8178985 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.1206. Min Act: -0.1700
Data Index: 2345968 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.1206. Min Act: -0.1700
Data Index: 1694108 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.0581. Min Act: -0.1700
Data Index: 4354219 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.0581. Min Act: -0.1700
Data Index: 1399580 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9019. Min Range: -7.9019
Max Act: 7.0269. Min Act: -0.1700
Data Index: 5490474 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9019. Min Range: -7.9019
Max Act: 6.9644. Min Act: -0.1700
Data Index: 1243733 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9019. Min Range: -7.9019
Max Act: 6.9644. Min Act: -0.1700
Data Index: 4211286 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9019. Min Range: -7.9019
Max Act: 6.9644. Min Act: -0.1700
Data Index: 441588 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9019. Min Range: -7.9019
Max Act: 6.9644. Min Act: -0.1700
Data Index: 3221523 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19