Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 507 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0180. Min Range: -7.0180
Max Act: 7.0180. Min Act: -0.1700
Data Index: 4439768 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.4868. Min Act: -0.1700
Data Index: 5812268 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.3618. Min Act: -0.1700
Data Index: 4329517 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.2993. Min Act: -0.1700
Data Index: 6448061 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.2993. Min Act: -0.1700
Data Index: 1986609 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1743. Min Act: -0.1700
Data Index: 5680372 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1430. Min Act: -0.1700
Data Index: 4514249 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 3933111 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.0805. Min Act: -0.1700
Data Index: 801850 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 2199081 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 6889878 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 7263586 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 3342966 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 279642 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 6137384 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.1118. Min Act: -0.1700
Data Index: 4732509 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.0805. Min Act: -0.1700
Data Index: 8623847 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.0805. Min Act: -0.1700
Data Index: 2093297 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.0805. Min Act: -0.1700
Data Index: 8600128 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0180. Min Range: -7.0180
Max Act: 6.0493. Min Act: -0.1700
Data Index: 3694589 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19