Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1092 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1704. Min Range: -8.1704
Max Act: 8.1704. Min Act: -0.1700
Data Index: 4718504 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.9829. Min Act: -0.1700
Data Index: 7627278 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.9204. Min Act: -0.1700
Data Index: 1083987 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.7954. Min Act: -0.1700
Data Index: 4163968 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.7954. Min Act: -0.1700
Data Index: 2596857 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.7954. Min Act: -0.1700
Data Index: 3688295 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.7017. Min Act: -0.1700
Data Index: 1005156 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.6392. Min Act: -0.1700
Data Index: 496169 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.6392. Min Act: -0.1700
Data Index: 7680918 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.6079. Min Act: -0.1700
Data Index: 6701702 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.5454. Min Act: -0.1700
Data Index: 577231 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.5454. Min Act: -0.1700
Data Index: 1979591 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.5454. Min Act: -0.1700
Data Index: 8621479 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.5142. Min Act: -0.1700
Data Index: 7670718 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.5142. Min Act: -0.1700
Data Index: 4644777 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.4829. Min Act: -0.1700
Data Index: 7868738 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.4829. Min Act: -0.1700
Data Index: 6697043 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.4829. Min Act: -0.1700
Data Index: 3044560 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.4517. Min Act: -0.1700
Data Index: 4640545 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1704. Min Range: -8.1704
Max Act: 7.4517. Min Act: -0.1700
Data Index: 3765308 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19