Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.5717. Min Act: -0.1700
Data Index: 5767878 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.5404. Min Act: -0.1700
Data Index: 8168504 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.5092. Min Act: -0.1700
Data Index: 5741299 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.4779. Min Act: -0.1700
Data Index: 5970830 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.4779. Min Act: -0.1700
Data Index: 4524559 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.4467. Min Act: -0.1700
Data Index: 5982672 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.4154. Min Act: -0.1700
Data Index: 676890 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.4467. Min Act: -0.1700
Data Index: 2044423 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.3842. Min Act: -0.1700
Data Index: 8494036 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.3529. Min Act: -0.1700
Data Index: 3472520 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.3529. Min Act: -0.1700
Data Index: 2630598 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.3217. Min Act: -0.1700
Data Index: 1095203 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.2904. Min Act: -0.1700
Data Index: 206975 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.3217. Min Act: -0.1700
Data Index: 5188641 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.2592. Min Act: -0.1700
Data Index: 5499906 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.2904. Min Act: -0.1700
Data Index: 7412550 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.2904. Min Act: -0.1700
Data Index: 2627213 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.2904. Min Act: -0.1700
Data Index: 6468355 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.2904. Min Act: -0.1700
Data Index: 3669831 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5717. Min Range: -6.5717
Max Act: 6.3217. Min Act: -0.1700
Data Index: 2522352 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19