Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.8740. Min Act: -0.1700
Data Index: 1340185 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.8115. Min Act: -0.1700
Data Index: 6262785 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.8428. Min Act: -0.1700
Data Index: 4654054 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.5615. Min Act: -0.1700
Data Index: 1433572 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.5615. Min Act: -0.1700
Data Index: 4719108 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.5303. Min Act: -0.1700
Data Index: 6381671 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.5303. Min Act: -0.1700
Data Index: 801472 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.5303. Min Act: -0.1700
Data Index: 4291855 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.5303. Min Act: -0.1700
Data Index: 3136687 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4990. Min Act: -0.1700
Data Index: 687550 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4678. Min Act: -0.1700
Data Index: 3526175 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4990. Min Act: -0.1700
Data Index: 5031951 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4990. Min Act: -0.1700
Data Index: 4148883 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4678. Min Act: -0.1700
Data Index: 5153112 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4365. Min Act: -0.1700
Data Index: 3194236 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4053. Min Act: -0.1700
Data Index: 1895354 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4365. Min Act: -0.1700
Data Index: 4166728 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4365. Min Act: -0.1700
Data Index: 4709048 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4053. Min Act: -0.1700
Data Index: 4250675 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8740. Min Range: -6.8740
Max Act: 6.4053. Min Act: -0.1700
Data Index: 4548526 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19