Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 543 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.6220. Min Act: -0.1700
Data Index: 5653723 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.6533. Min Act: -0.1700
Data Index: 4126778 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.4970. Min Act: -0.1700
Data Index: 7658607 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.4033. Min Act: -0.1700
Data Index: 147178 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.4033. Min Act: -0.1700
Data Index: 1793779 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.3720. Min Act: -0.1700
Data Index: 524805 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.3408. Min Act: -0.1700
Data Index: 1569776 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.3408. Min Act: -0.1700
Data Index: 3637091 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.3095. Min Act: -0.1700
Data Index: 4463789 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.2783. Min Act: -0.1700
Data Index: 3929335 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.2158. Min Act: -0.1700
Data Index: 4636349 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.2158. Min Act: -0.1700
Data Index: 1071234 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.1845. Min Act: -0.1700
Data Index: 8236566 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.1533. Min Act: -0.1700
Data Index: 8468784 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.1533. Min Act: -0.1700
Data Index: 4368375 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.1533. Min Act: -0.1700
Data Index: 2328592 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.1533. Min Act: -0.1700
Data Index: 7732872 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.1220. Min Act: -0.1700
Data Index: 5706653 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.0908. Min Act: -0.1700
Data Index: 1530038 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6533. Min Range: -6.6533
Max Act: 6.1533. Min Act: -0.1700
Data Index: 2011989 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19