Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1095 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.6732. Min Act: -0.1700
Data Index: 2655363 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.5482. Min Act: -0.1700
Data Index: 3094716 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.4232. Min Act: -0.1700
Data Index: 7376564 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.2357. Min Act: -0.1700
Data Index: 3945343 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.2357. Min Act: -0.1700
Data Index: 4269111 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.2357. Min Act: -0.1700
Data Index: 3945331 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.1732. Min Act: -0.1700
Data Index: 3732264 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.1732. Min Act: -0.1700
Data Index: 7387241 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.1732. Min Act: -0.1700
Data Index: 248380 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.1732. Min Act: -0.1700
Data Index: 7093794 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.1732. Min Act: -0.1700
Data Index: 8321722 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.1107. Min Act: -0.1700
Data Index: 3265987 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.1107. Min Act: -0.1700
Data Index: 5699763 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.0482. Min Act: -0.1700
Data Index: 6946238 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.0482. Min Act: -0.1700
Data Index: 8312935 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6732. Min Range: -10.6732
Max Act: 10.0482. Min Act: -0.1700
Data Index: 7748702 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6732. Min Range: -10.6732
Max Act: 9.9857. Min Act: -0.1700
Data Index: 7093787 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6732. Min Range: -10.6732
Max Act: 9.9857. Min Act: -0.1700
Data Index: 5971445 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6732. Min Range: -10.6732
Max Act: 9.9857. Min Act: -0.1700
Data Index: 7748703 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6732. Min Range: -10.6732
Max Act: 9.9232. Min Act: -0.1700
Data Index: 7093801 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19