Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.3885. Min Act: -0.1700
Data Index: 5508497 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.3572. Min Act: -0.1700
Data Index: 1454742 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.3260. Min Act: -0.1700
Data Index: 2841908 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.2322. Min Act: -0.1700
Data Index: 801143 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.2322. Min Act: -0.1700
Data Index: 6518285 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.2010. Min Act: -0.1700
Data Index: 7683484 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1697. Min Act: -0.1700
Data Index: 1979600 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1697. Min Act: -0.1700
Data Index: 3113489 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1697. Min Act: -0.1700
Data Index: 5580055 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1385. Min Act: -0.1700
Data Index: 5239850 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1072. Min Act: -0.1700
Data Index: 5033077 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1385. Min Act: -0.1689
Data Index: 6476539 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1385. Min Act: -0.1700
Data Index: 8798337 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1072. Min Act: -0.1700
Data Index: 2800632 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1072. Min Act: -0.1700
Data Index: 8828366 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1385. Min Act: -0.1698
Data Index: 1226996 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.1072. Min Act: -0.1700
Data Index: 2472363 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.0760. Min Act: -0.1700
Data Index: 1902116 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.0760. Min Act: -0.1700
Data Index: 7378827 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3885. Min Range: -5.3885
Max Act: 5.0760. Min Act: -0.1700
Data Index: 2240072 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19