Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.5770. Min Act: -0.1700
Data Index: 6617923 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.3895. Min Act: -0.1700
Data Index: 3383620 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.3583. Min Act: -0.1700
Data Index: 7727850 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.2958. Min Act: -0.1700
Data Index: 851541 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.3270. Min Act: -0.1700
Data Index: 5368308 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.2333. Min Act: -0.1700
Data Index: 743065 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.2333. Min Act: -0.1700
Data Index: 952760 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.1395. Min Act: -0.1700
Data Index: 794809 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.1083. Min Act: -0.1700
Data Index: 4639320 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.1083. Min Act: -0.1700
Data Index: 8765417 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.1083. Min Act: -0.1700
Data Index: 7447698 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.0145. Min Act: -0.1700
Data Index: 2510616 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9833. Min Act: -0.1700
Data Index: 3279516 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9208. Min Act: -0.1700
Data Index: 3037639 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 2821215 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 600646 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 813264 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 1180366 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9208. Min Act: -0.1700
Data Index: 8462746 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.8895. Min Act: -0.1700
Data Index: 7058044 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19