Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1881 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.8995. Min Act: -0.1700
Data Index: 3434640 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.8057. Min Act: -0.1700
Data Index: 8549661 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.7120. Min Act: -0.1700
Data Index: 7298067 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.5870. Min Act: -0.1700
Data Index: 4575275 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.5557. Min Act: -0.1700
Data Index: 4082293 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.5557. Min Act: -0.1700
Data Index: 2517665 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.5245. Min Act: -0.1700
Data Index: 3488328 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4932. Min Act: -0.1700
Data Index: 7200849 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4932. Min Act: -0.1700
Data Index: 3322728 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4620. Min Act: -0.1700
Data Index: 588557 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4932. Min Act: -0.1700
Data Index: 7200852 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4307. Min Act: -0.1700
Data Index: 2796453 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4307. Min Act: -0.1700
Data Index: 8277077 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4307. Min Act: -0.1700
Data Index: 2967306 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4307. Min Act: -0.1700
Data Index: 66217 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4307. Min Act: -0.1700
Data Index: 1998548 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.4307. Min Act: -0.1700
Data Index: 5881007 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.3995. Min Act: -0.1700
Data Index: 5913954 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.3995. Min Act: -0.1700
Data Index: 1138475 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8995. Min Range: -6.8995
Max Act: 6.3682. Min Act: -0.1700
Data Index: 534772 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19