Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.4807. Min Act: -0.1700
Data Index: 5068636 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3869. Min Act: -0.1700
Data Index: 6850265 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3557. Min Act: -0.1700
Data Index: 909788 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3244. Min Act: -0.1700
Data Index: 3259191 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3244. Min Act: -0.1700
Data Index: 3832039 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.3244. Min Act: -0.1700
Data Index: 1425291 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 1170528 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2932. Min Act: -0.1700
Data Index: 6237901 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2619. Min Act: -0.1700
Data Index: 7534320 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2619. Min Act: -0.1700
Data Index: 6340132 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2619. Min Act: -0.1700
Data Index: 5123275 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2307. Min Act: -0.1700
Data Index: 8511984 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2307. Min Act: -0.1700
Data Index: 3645299 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2307. Min Act: -0.1700
Data Index: 8416345 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2307. Min Act: -0.1700
Data Index: 7132601 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.2307. Min Act: -0.1700
Data Index: 763598 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.1994. Min Act: -0.1700
Data Index: 7861640 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.1994. Min Act: -0.1700
Data Index: 7806127 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.1994. Min Act: -0.1700
Data Index: 814106 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4807. Min Range: -4.4807
Max Act: 4.1994. Min Act: -0.1700
Data Index: 3090873 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19