Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.4747. Min Range: -10.4747
Max Act: 10.4747. Min Act: -0.1700
Data Index: 1662353 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.4747. Min Act: -0.1700
Data Index: 2411464 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.4122. Min Act: -0.1700
Data Index: 8655774 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.4122. Min Act: -0.1700
Data Index: 4934016 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.4122. Min Act: -0.1700
Data Index: 4624803 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.3497. Min Act: -0.1700
Data Index: 3354219 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.2872. Min Act: -0.1700
Data Index: 1081265 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.2247. Min Act: -0.1700
Data Index: 3517450 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.0997. Min Act: -0.1700
Data Index: 5117276 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.1622. Min Act: -0.1700
Data Index: 6490656 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.0997. Min Act: -0.1700
Data Index: 5703953 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4747. Min Range: -10.4747
Max Act: 9.0372. Min Act: -0.1700
Data Index: 7742036 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.9122. Min Act: -0.1700
Data Index: 550692 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.8497. Min Act: -0.1700
Data Index: 6728341 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.9747. Min Act: -0.1700
Data Index: 6006693 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.9747. Min Act: -0.1700
Data Index: 3718650 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.8497. Min Act: -0.1700
Data Index: 6843291 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.9122. Min Act: -0.1700
Data Index: 7685868 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.9747. Min Act: -0.1700
Data Index: 3013590 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4747. Min Range: -10.4747
Max Act: 8.7872. Min Act: -0.1700
Data Index: 7347698 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19