Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.5906. Min Act: -0.1700
Data Index: 917613 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4969. Min Act: -0.1700
Data Index: 6310989 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4656. Min Act: -0.1700
Data Index: 1137527 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4969. Min Act: -0.1700
Data Index: 460996 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4969. Min Act: -0.1700
Data Index: 5978824 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4344. Min Act: -0.1700
Data Index: 5065468 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.3719. Min Act: -0.1700
Data Index: 4525041 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4031. Min Act: -0.1700
Data Index: 8797977 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4031. Min Act: -0.1700
Data Index: 7613006 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.4031. Min Act: -0.1700
Data Index: 5887856 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.3719. Min Act: -0.1700
Data Index: 4396873 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.3719. Min Act: -0.1700
Data Index: 3135286 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.3719. Min Act: -0.1700
Data Index: 3608704 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.3406. Min Act: -0.1700
Data Index: 3406629 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.3094. Min Act: -0.1700
Data Index: 7355118 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.2781. Min Act: -0.1700
Data Index: 4034445 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.2781. Min Act: -0.1700
Data Index: 7455423 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.2781. Min Act: -0.1700
Data Index: 6942829 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.2781. Min Act: -0.1700
Data Index: 62705 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5906. Min Range: -7.5906
Max Act: 7.2781. Min Act: -0.1700
Data Index: 5127589 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19