Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0055. Min Range: -5.0055
Max Act: 5.0055. Min Act: -0.1700
Data Index: 7710241 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9743. Min Act: -0.1700
Data Index: 5577408 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9743. Min Act: -0.1700
Data Index: 4839048 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 2422851 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 3613410 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9118. Min Act: -0.1700
Data Index: 1796436 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9118. Min Act: -0.1700
Data Index: 3419196 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9118. Min Act: -0.1700
Data Index: 6817854 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9118. Min Act: -0.1700
Data Index: 308375 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 8281743 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.8805. Min Act: -0.1700
Data Index: 1690560 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.8805. Min Act: -0.1700
Data Index: 7412245 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.8805. Min Act: -0.1700
Data Index: 1240576 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.8180. Min Act: -0.1700
Data Index: 3536202 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.8805. Min Act: -0.1700
Data Index: 1150605 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.8493. Min Act: -0.1700
Data Index: 6747590 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.8180. Min Act: -0.1700
Data Index: 8814464 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7868. Min Act: -0.1700
Data Index: 5366952 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7868. Min Act: -0.1700
Data Index: 1310718 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7868. Min Act: -0.1700
Data Index: 5742760 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19