Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.3305. Min Act: -0.1700
Data Index: 2120303 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.2680. Min Act: -0.1700
Data Index: 2277008 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0492. Min Act: -0.1700
Data Index: 1579891 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0492. Min Act: -0.1700
Data Index: 6383763 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0492. Min Act: -0.1700
Data Index: 1579896 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0492. Min Act: -0.1700
Data Index: 3342677 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0492. Min Act: -0.1700
Data Index: 8007909 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0492. Min Act: -0.1700
Data Index: 2090762 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0180. Min Act: -0.1700
Data Index: 2097113 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0180. Min Act: -0.1700
Data Index: 853405 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.9867. Min Act: -0.1700
Data Index: 3723455 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.9555. Min Act: -0.1700
Data Index: 8556074 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.9242. Min Act: -0.1700
Data Index: 3555844 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.8930. Min Act: -0.1700
Data Index: 4991725 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.8930. Min Act: -0.1700
Data Index: 4268325 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.8617. Min Act: -0.1700
Data Index: 2498461 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.8617. Min Act: -0.1700
Data Index: 1374542 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.8305. Min Act: -0.1700
Data Index: 4907521 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.8305. Min Act: -0.1700
Data Index: 4089002 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3305. Min Range: -5.3305
Max Act: 4.8305. Min Act: -0.1700
Data Index: 1275866 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19