Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2076 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.5921. Min Act: -0.1700
Data Index: 2050096 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.5296. Min Act: -0.1700
Data Index: 1481949 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.4046. Min Act: -0.1700
Data Index: 8612064 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.3734. Min Act: -0.1700
Data Index: 1907611 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.2171. Min Act: -0.1700
Data Index: 3211896 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.2171. Min Act: -0.1700
Data Index: 2241924 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.1859. Min Act: -0.1700
Data Index: 6511134 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.1546. Min Act: -0.1700
Data Index: 8263682 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.1234. Min Act: -0.1700
Data Index: 308335 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.0921. Min Act: -0.1700
Data Index: 4597360 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.0609. Min Act: -0.1700
Data Index: 1602403 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.0609. Min Act: -0.1700
Data Index: 1856474 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.0609. Min Act: -0.1700
Data Index: 2644041 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.0296. Min Act: -0.1700
Data Index: 2050095 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5921. Min Range: -7.5921
Max Act: 7.0296. Min Act: -0.1700
Data Index: 1575240 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5921. Min Range: -7.5921
Max Act: 6.9984. Min Act: -0.1700
Data Index: 6861159 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5921. Min Range: -7.5921
Max Act: 6.9984. Min Act: -0.1700
Data Index: 7054723 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5921. Min Range: -7.5921
Max Act: 6.9671. Min Act: -0.1700
Data Index: 1476205 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5921. Min Range: -7.5921
Max Act: 6.9359. Min Act: -0.1700
Data Index: 2554798 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5921. Min Range: -7.5921
Max Act: 6.9359. Min Act: -0.1700
Data Index: 4071727 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19