Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6053 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0942. Min Range: -7.0942
Max Act: 7.0942. Min Act: -0.1700
Data Index: 6400045 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0942. Min Range: -7.0942
Max Act: 7.0317. Min Act: -0.1700
Data Index: 8410784 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0942. Min Range: -7.0942
Max Act: 7.0004. Min Act: -0.1700
Data Index: 4241102 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0942. Min Range: -7.0942
Max Act: 7.0004. Min Act: -0.1700
Data Index: 5127281 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0942. Min Range: -7.0942
Max Act: 7.0004. Min Act: -0.1700
Data Index: 2993673 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.9692. Min Act: -0.1700
Data Index: 4158313 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.9379. Min Act: -0.1700
Data Index: 1092537 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.9379. Min Act: -0.1700
Data Index: 6734390 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.9379. Min Act: -0.1700
Data Index: 3357689 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.8754. Min Act: -0.1700
Data Index: 635588 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.8442. Min Act: -0.1700
Data Index: 946098 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.8442. Min Act: -0.1700
Data Index: 6809755 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.8442. Min Act: -0.1700
Data Index: 635886 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.8754. Min Act: -0.1700
Data Index: 5755291 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.8129. Min Act: -0.1700
Data Index: 1195028 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.7817. Min Act: -0.1700
Data Index: 2506608 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.7504. Min Act: -0.1700
Data Index: 2283561 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.7504. Min Act: -0.1700
Data Index: 6861464 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.7504. Min Act: -0.1700
Data Index: 5855508 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0942. Min Range: -7.0942
Max Act: 6.7504. Min Act: -0.1700
Data Index: 3661895 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19