Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.8551. Min Act: -0.1700
Data Index: 157778 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.2926. Min Act: -0.1700
Data Index: 4957475 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.2301. Min Act: -0.1700
Data Index: 2210229 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.1676. Min Act: -0.1700
Data Index: 1573536 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.1051. Min Act: -0.1700
Data Index: 3980849 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.1051. Min Act: -0.1700
Data Index: 7552484 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 7686662 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 506042 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 3526251 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 1075670 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8551. Min Range: -9.8551
Max Act: 8.9801. Min Act: -0.1700
Data Index: 8155885 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 289751 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 6358473 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 4629577 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 7449003 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 3838771 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8551. Min Range: -9.8551
Max Act: 9.0426. Min Act: -0.1700
Data Index: 1344388 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8551. Min Range: -9.8551
Max Act: 8.9801. Min Act: -0.1700
Data Index: 1641091 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8551. Min Range: -9.8551
Max Act: 8.9801. Min Act: -0.1700
Data Index: 2275267 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8551. Min Range: -9.8551
Max Act: 8.9801. Min Act: -0.1700
Data Index: 5207188 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19