Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.3992. Min Act: -0.1700
Data Index: 7038037 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.2742. Min Act: -0.1700
Data Index: 6543022 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.2742. Min Act: -0.1700
Data Index: 5899809 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.0867. Min Act: -0.1700
Data Index: 1094795 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.0242. Min Act: -0.1700
Data Index: 645706 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.0242. Min Act: -0.1700
Data Index: 5592198 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.0242. Min Act: -0.1700
Data Index: 5580276 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3992. Min Range: -9.3992
Max Act: 9.0242. Min Act: -0.1700
Data Index: 2083817 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.9617. Min Act: -0.1700
Data Index: 5164655 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.9617. Min Act: -0.1700
Data Index: 1237383 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.8992. Min Act: -0.1700
Data Index: 8277504 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.8992. Min Act: -0.1700
Data Index: 1859755 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.8992. Min Act: -0.1700
Data Index: 6203227 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.7742. Min Act: -0.1700
Data Index: 5523314 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.7742. Min Act: -0.1700
Data Index: 5756585 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.7117. Min Act: -0.1700
Data Index: 7250849 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.6492. Min Act: -0.1700
Data Index: 3171120 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.6492. Min Act: -0.1700
Data Index: 574123 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.6492. Min Act: -0.1700
Data Index: 3956394 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3992. Min Range: -9.3992
Max Act: 8.6492. Min Act: -0.1700
Data Index: 3357699 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19