Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6340 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.8556. Min Act: -0.1700
Data Index: 2882966 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.6056. Min Act: -0.1700
Data Index: 929706 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.6056. Min Act: -0.1700
Data Index: 7228070 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.5431. Min Act: -0.1700
Data Index: 1856055 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.3556. Min Act: -0.1700
Data Index: 2372780 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.3556. Min Act: -0.1700
Data Index: 4025303 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.2306. Min Act: -0.1700
Data Index: 2280999 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.2306. Min Act: -0.1700
Data Index: 1757355 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.2306. Min Act: -0.1700
Data Index: 7549733 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.2306. Min Act: -0.1700
Data Index: 80108 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.2306. Min Act: -0.1700
Data Index: 6300367 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.1681. Min Act: -0.1700
Data Index: 7168171 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.1681. Min Act: -0.1700
Data Index: 3164674 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.2306. Min Act: -0.1700
Data Index: 5712914 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.1056. Min Act: -0.1700
Data Index: 5889330 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.1056. Min Act: -0.1700
Data Index: 539898 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.0431. Min Act: -0.1700
Data Index: 4212197 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.0431. Min Act: -0.1700
Data Index: 376511 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.0431. Min Act: -0.1700
Data Index: 2619233 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8556. Min Range: -8.8556
Max Act: 8.0431. Min Act: -0.1700
Data Index: 1041167 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19