Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 940 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0464. Min Range: -5.0464
Max Act: 5.0464. Min Act: -0.1700
Data Index: 8013 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7964. Min Act: -0.1700
Data Index: 7012220 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7652. Min Act: -0.1700
Data Index: 4387135 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7652. Min Act: -0.1700
Data Index: 3279268 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7339. Min Act: -0.1700
Data Index: 5339928 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7027. Min Act: -0.1700
Data Index: 8379845 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7027. Min Act: -0.1700
Data Index: 8223237 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7027. Min Act: -0.1700
Data Index: 2426107 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.7027. Min Act: -0.1700
Data Index: 4413392 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.6714. Min Act: -0.1700
Data Index: 4361513 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.6402. Min Act: -0.1700
Data Index: 2597096 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.5777. Min Act: -0.1700
Data Index: 2705877 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.5777. Min Act: -0.1700
Data Index: 3146856 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.5152. Min Act: -0.1700
Data Index: 6397699 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.5464. Min Act: -0.1700
Data Index: 1485121 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.5152. Min Act: -0.1700
Data Index: 2934399 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.4839. Min Act: -0.1700
Data Index: 7911744 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.4527. Min Act: -0.1700
Data Index: 5709244 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.4839. Min Act: -0.1700
Data Index: 5997828 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0464. Min Range: -5.0464
Max Act: 4.4214. Min Act: -0.1700
Data Index: 2560450 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19