Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2178 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5921. Min Range: -6.5921
Max Act: 6.5921. Min Act: -0.1700
Data Index: 4380052 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5921. Min Range: -6.5921
Max Act: 6.3109. Min Act: -0.1700
Data Index: 6366897 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5921. Min Range: -6.5921
Max Act: 6.2171. Min Act: -0.1700
Data Index: 8497737 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5921. Min Range: -6.5921
Max Act: 6.1859. Min Act: -0.1700
Data Index: 8279757 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5921. Min Range: -6.5921
Max Act: 6.1234. Min Act: -0.1700
Data Index: 8645979 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5921. Min Range: -6.5921
Max Act: 6.0296. Min Act: -0.1700
Data Index: 3000814 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 2716356 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 2042123 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.8734. Min Act: -0.1700
Data Index: 8503935 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.8109. Min Act: -0.1700
Data Index: 6839191 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.7796. Min Act: -0.1700
Data Index: 8017411 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.7484. Min Act: -0.1700
Data Index: 1481649 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.7484. Min Act: -0.1700
Data Index: 5801915 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.6859. Min Act: -0.1700
Data Index: 3617842 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.7171. Min Act: -0.1700
Data Index: 3098972 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.6859. Min Act: -0.1700
Data Index: 4212815 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.6859. Min Act: -0.1700
Data Index: 1708374 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.6546. Min Act: -0.1700
Data Index: 7605088 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.6234. Min Act: -0.1700
Data Index: 1666945 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5921. Min Range: -6.5921
Max Act: 5.6234. Min Act: -0.1700
Data Index: 2088064 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19