Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 611 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4504. Min Range: -7.4504
Max Act: 7.4504. Min Act: -0.1700
Data Index: 370332 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4504. Min Range: -7.4504
Max Act: 7.4192. Min Act: -0.1700
Data Index: 7964917 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4504. Min Range: -7.4504
Max Act: 7.0754. Min Act: -0.1700
Data Index: 6215786 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.8879. Min Act: -0.1700
Data Index: 2139404 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.8567. Min Act: -0.1700
Data Index: 5244770 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.8567. Min Act: -0.1700
Data Index: 4096759 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.8254. Min Act: -0.1700
Data Index: 6609936 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.8567. Min Act: -0.1700
Data Index: 2514007 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.8567. Min Act: -0.1700
Data Index: 3090613 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.8254. Min Act: -0.1700
Data Index: 1841838 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7629. Min Act: -0.1700
Data Index: 2140979 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7629. Min Act: -0.1700
Data Index: 2767396 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7942. Min Act: -0.1700
Data Index: 8202275 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7317. Min Act: -0.1700
Data Index: 3882733 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7317. Min Act: -0.1700
Data Index: 1280444 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7317. Min Act: -0.1700
Data Index: 4426093 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7004. Min Act: -0.1700
Data Index: 1031447 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7004. Min Act: -0.1700
Data Index: 947734 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.7004. Min Act: -0.1700
Data Index: 8069082 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4504. Min Range: -7.4504
Max Act: 6.6692. Min Act: -0.1700
Data Index: 8255269 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19