Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.2325. Min Act: -0.1699
Data Index: 2091010 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.2325. Min Act: -0.1700
Data Index: 7113110 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.2012. Min Act: -0.1700
Data Index: 394342 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.2012. Min Act: -0.1700
Data Index: 2557322 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.1387. Min Act: -0.1700
Data Index: 7048487 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.1700. Min Act: -0.1700
Data Index: 2101097 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.1700. Min Act: -0.1700
Data Index: 1171953 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.1075. Min Act: -0.1700
Data Index: 6288930 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.1075. Min Act: -0.1700
Data Index: 2192989 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.1075. Min Act: -0.1700
Data Index: 4967022 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0762. Min Act: -0.1700
Data Index: 1315161 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0762. Min Act: -0.1700
Data Index: 5755108 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0762. Min Act: -0.1700
Data Index: 4310887 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0762. Min Act: -0.1700
Data Index: 7607124 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0762. Min Act: -0.1700
Data Index: 6005832 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0450. Min Act: -0.1700
Data Index: 241034 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0137. Min Act: -0.1700
Data Index: 6545424 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6930032 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6522722 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2325. Min Range: -5.2325
Max Act: 5.0137. Min Act: -0.1700
Data Index: 193447 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19