Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.5942. Min Act: -0.1700
Data Index: 1698708 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.3129. Min Act: -0.1700
Data Index: 1351194 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1567. Min Act: -0.1700
Data Index: 4765887 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.0317. Min Act: -0.1700
Data Index: 8657365 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.0004. Min Act: -0.1700
Data Index: 1305563 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.0004. Min Act: -0.1700
Data Index: 2884217 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.9692. Min Act: -0.1700
Data Index: 43936 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.9379. Min Act: -0.1700
Data Index: 7734984 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.9379. Min Act: -0.1700
Data Index: 8351667 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.9379. Min Act: -0.1700
Data Index: 5819829 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.9379. Min Act: -0.1700
Data Index: 3964589 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.9067. Min Act: -0.1700
Data Index: 4022052 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4094069 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.8442. Min Act: -0.1700
Data Index: 1328780 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.8442. Min Act: -0.1700
Data Index: 3412629 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.8129. Min Act: -0.1700
Data Index: 8302577 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.8442. Min Act: -0.1700
Data Index: 761934 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.8129. Min Act: -0.1700
Data Index: 7035001 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4930636 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5942. Min Range: -5.5942
Max Act: 4.7817. Min Act: -0.1700
Data Index: 6183913 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19