Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.9895. Min Act: -0.1700
Data Index: 4947168 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.8020. Min Act: -0.1700
Data Index: 1198257 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7707. Min Act: -0.1700
Data Index: 5852549 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7082. Min Act: -0.1700
Data Index: 259355 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7395. Min Act: -0.1700
Data Index: 3584253 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7395. Min Act: -0.1700
Data Index: 4915874 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7395. Min Act: -0.1700
Data Index: 2969303 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7082. Min Act: -0.1700
Data Index: 8484523 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7082. Min Act: -0.1700
Data Index: 1065852 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.6770. Min Act: -0.1700
Data Index: 6875793 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.6770. Min Act: -0.1700
Data Index: 1771045 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.7082. Min Act: -0.1700
Data Index: 4702739 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.6145. Min Act: -0.1700
Data Index: 594100 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.6145. Min Act: -0.1700
Data Index: 4309514 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.5832. Min Act: -0.1700
Data Index: 1886896 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.5520. Min Act: -0.1700
Data Index: 2479969 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.5207. Min Act: -0.1700
Data Index: 3886588 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.5520. Min Act: -0.1700
Data Index: 6023622 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.5207. Min Act: -0.1700
Data Index: 1236263 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9895. Min Range: -6.9895
Max Act: 6.5207. Min Act: -0.1700
Data Index: 342849 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19