Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.9390. Min Act: -0.1700
Data Index: 6585243 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.8765. Min Act: -0.1700
Data Index: 2203217 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.8452. Min Act: -0.1700
Data Index: 722821 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.8452. Min Act: -0.1700
Data Index: 3973246 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.8452. Min Act: -0.1700
Data Index: 3157177 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7515. Min Act: -0.1700
Data Index: 879476 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7202. Min Act: -0.1700
Data Index: 4505244 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7202. Min Act: -0.1700
Data Index: 618870 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.6890. Min Act: -0.1700
Data Index: 651993 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7202. Min Act: -0.1700
Data Index: 2958791 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7202. Min Act: -0.1700
Data Index: 3440429 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7202. Min Act: -0.1700
Data Index: 3476065 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7202. Min Act: -0.1700
Data Index: 3770761 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.7202. Min Act: -0.1700
Data Index: 185943 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.6890. Min Act: -0.1700
Data Index: 4372366 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.6890. Min Act: -0.1700
Data Index: 7169555 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.6890. Min Act: -0.1700
Data Index: 5230280 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.6577. Min Act: -0.1700
Data Index: 109326 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.6577. Min Act: -0.1700
Data Index: 65969 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9390. Min Range: -4.9390
Max Act: 4.6577. Min Act: -0.1700
Data Index: 3865183 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19