Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 837 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1053. Min Range: -3.1053
Max Act: 3.1053. Min Act: -0.1700
Data Index: 5239351 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1053. Min Range: -3.1053
Max Act: 3.0895. Min Act: -0.1700
Data Index: 3571306 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9948. Min Act: -0.1700
Data Index: 2985156 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9790. Min Act: -0.1700
Data Index: 6184245 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9632. Min Act: -0.1700
Data Index: 1581372 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9632. Min Act: -0.1700
Data Index: 4257221 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9156. Min Act: -0.1700
Data Index: 8194159 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9473. Min Act: -0.1700
Data Index: 1997498 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8998. Min Act: -0.1700
Data Index: 3246906 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9156. Min Act: -0.1700
Data Index: 6632010 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9156. Min Act: -0.1700
Data Index: 5429959 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8839. Min Act: -0.1700
Data Index: 8383866 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.9156. Min Act: -0.1700
Data Index: 383686 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8998. Min Act: -0.1700
Data Index: 3483299 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8681. Min Act: -0.1700
Data Index: 8092551 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8522. Min Act: -0.1700
Data Index: 5484897 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8363. Min Act: -0.1700
Data Index: 391495 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8363. Min Act: -0.1700
Data Index: 6143802 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8522. Min Act: -0.1700
Data Index: 2380495 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1053. Min Range: -3.1053
Max Act: 2.8522. Min Act: -0.1700
Data Index: 2460201 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19