Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3837. Min Range: -7.3837
Max Act: 7.3837. Min Act: -0.1700
Data Index: 7784489 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3837. Min Range: -7.3837
Max Act: 7.3212. Min Act: -0.1700
Data Index: 8269309 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3837. Min Range: -7.3837
Max Act: 7.2587. Min Act: -0.1700
Data Index: 3297166 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3837. Min Range: -7.3837
Max Act: 7.2587. Min Act: -0.1700
Data Index: 4158720 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3837. Min Range: -7.3837
Max Act: 7.1962. Min Act: -0.1700
Data Index: 1614911 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3837. Min Range: -7.3837
Max Act: 7.0087. Min Act: -0.1700
Data Index: 8437218 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.9775. Min Act: -0.1700
Data Index: 4964717 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.9462. Min Act: -0.1700
Data Index: 6295917 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.9150. Min Act: -0.1700
Data Index: 6408517 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.9150. Min Act: -0.1700
Data Index: 2065628 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.8837. Min Act: -0.1700
Data Index: 2270077 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.8525. Min Act: -0.1700
Data Index: 636175 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.7900. Min Act: -0.1700
Data Index: 6679066 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.8212. Min Act: -0.1700
Data Index: 6609916 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.7900. Min Act: -0.1700
Data Index: 6119991 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.7900. Min Act: -0.1700
Data Index: 6347198 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.7587. Min Act: -0.1700
Data Index: 8135382 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.7587. Min Act: -0.1700
Data Index: 651411 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.7587. Min Act: -0.1700
Data Index: 4060822 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3837. Min Range: -7.3837
Max Act: 6.6962. Min Act: -0.1700
Data Index: 6912134 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19