Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3116. Min Range: -6.3116
Max Act: 6.3116. Min Act: -0.1700
Data Index: 1042015 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3116. Min Range: -6.3116
Max Act: 6.2178. Min Act: -0.1700
Data Index: 1893408 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3116. Min Range: -6.3116
Max Act: 6.0303. Min Act: -0.1700
Data Index: 6161647 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3116. Min Range: -6.3116
Max Act: 6.0303. Min Act: -0.1700
Data Index: 498405 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3116. Min Range: -6.3116
Max Act: 6.0303. Min Act: -0.1700
Data Index: 7591086 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9991. Min Act: -0.1700
Data Index: 5702309 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9991. Min Act: -0.1700
Data Index: 4760236 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9678. Min Act: -0.1700
Data Index: 1376979 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9678. Min Act: -0.1700
Data Index: 685795 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 4180619 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 325602 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9366. Min Act: -0.1700
Data Index: 7076039 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 1938719 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 8110605 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 5464011 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 4928448 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.9053. Min Act: -0.1700
Data Index: 7704218 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.8741. Min Act: -0.1700
Data Index: 3260894 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.8741. Min Act: -0.1700
Data Index: 3797432 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3116. Min Range: -6.3116
Max Act: 5.8741. Min Act: -0.1700
Data Index: 7649861 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19