Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4832 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4761. Min Range: -7.4761
Max Act: 7.4761. Min Act: -0.1700
Data Index: 1168256 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4761. Min Range: -7.4761
Max Act: 7.0386. Min Act: -0.1700
Data Index: 8122469 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.9761. Min Act: -0.1700
Data Index: 4518014 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.9136. Min Act: -0.1700
Data Index: 876954 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.8824. Min Act: -0.1700
Data Index: 1873306 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.7574. Min Act: -0.1700
Data Index: 6035574 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6949. Min Act: -0.1700
Data Index: 8716553 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6949. Min Act: -0.1700
Data Index: 6155619 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 73333 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 1240118 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 1870410 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6324. Min Act: -0.1700
Data Index: 2547480 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6324. Min Act: -0.1700
Data Index: 5124250 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.5699. Min Act: -0.1700
Data Index: 8085910 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.5386. Min Act: -0.1700
Data Index: 5220697 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.6011. Min Act: -0.1700
Data Index: 8086967 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.5699. Min Act: -0.1700
Data Index: 3300996 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.5699. Min Act: -0.1700
Data Index: 5611001 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.5386. Min Act: -0.1700
Data Index: 1518633 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4761. Min Range: -7.4761
Max Act: 6.5386. Min Act: -0.1700
Data Index: 4820071 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19