Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.7023. Min Act: -0.1700
Data Index: 7363061 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.7023. Min Act: -0.1700
Data Index: 8167811 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.6710. Min Act: -0.1700
Data Index: 738987 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.3898. Min Act: -0.1700
Data Index: 2173528 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.3273. Min Act: -0.1700
Data Index: 8025611 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.1710. Min Act: -0.1700
Data Index: 5703186 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.1710. Min Act: -0.1700
Data Index: 1905821 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.1398. Min Act: -0.1700
Data Index: 7106875 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.1398. Min Act: -0.1700
Data Index: 7877102 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.1085. Min Act: -0.1700
Data Index: 8016799 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.1085. Min Act: -0.1700
Data Index: 4504663 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7772781 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0460. Min Act: -0.1700
Data Index: 7213957 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0773. Min Act: -0.1700
Data Index: 3351686 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0460. Min Act: -0.1700
Data Index: 6029899 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0148. Min Act: -0.1700
Data Index: 1050316 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0460. Min Act: -0.1700
Data Index: 3321478 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0460. Min Act: -0.1700
Data Index: 328341 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0148. Min Act: -0.1700
Data Index: 8201121 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7023. Min Range: -5.7023
Max Act: 5.0148. Min Act: -0.1700
Data Index: 8617087 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19