Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0369. Min Range: -8.0369
Max Act: 8.0369. Min Act: -0.1700
Data Index: 1087915 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.6306. Min Act: -0.1700
Data Index: 1934105 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.5994. Min Act: -0.1700
Data Index: 456341 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.5681. Min Act: -0.1700
Data Index: 3574478 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.5056. Min Act: -0.1700
Data Index: 1418425 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.4119. Min Act: -0.1700
Data Index: 8006554 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.3806. Min Act: -0.1700
Data Index: 2483503 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.3806. Min Act: -0.1700
Data Index: 3296416 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.3494. Min Act: -0.1700
Data Index: 3700131 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.2869. Min Act: -0.1700
Data Index: 3530156 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.1931. Min Act: -0.1700
Data Index: 7975628 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.2244. Min Act: -0.1700
Data Index: 1505039 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.1619. Min Act: -0.1700
Data Index: 3218784 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.1619. Min Act: -0.1700
Data Index: 5405669 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.1306. Min Act: -0.1700
Data Index: 244009 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.0994. Min Act: -0.1700
Data Index: 5407804 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.0681. Min Act: -0.1700
Data Index: 1282188 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.0681. Min Act: -0.1700
Data Index: 3373766 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.0369. Min Act: -0.1700
Data Index: 3494124 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0369. Min Range: -8.0369
Max Act: 7.0369. Min Act: -0.1700
Data Index: 246013 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19