Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.5205. Min Act: -0.1700
Data Index: 2659148 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.5205. Min Act: -0.1698
Data Index: 1032617 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.4580. Min Act: -0.1699
Data Index: 3825722 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3955. Min Act: -0.1700
Data Index: 8595308 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3955. Min Act: -0.1695
Data Index: 726810 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3955. Min Act: -0.1698
Data Index: 1641552 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3955. Min Act: -0.1700
Data Index: 1651798 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3955. Min Act: -0.1700
Data Index: 5955849 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 2287897 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 7255418 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 2260278 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1698
Data Index: 6737485 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1699
Data Index: 6373870 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1698
Data Index: 2212235 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 4504901 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 2513953 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1699
Data Index: 2488258 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 2337429 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 1591186 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5205. Min Range: -8.5205
Max Act: 8.3330. Min Act: -0.1700
Data Index: 1521660 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19