Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4856 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.7886. Min Act: -0.1700
Data Index: 8423451 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.7261. Min Act: -0.1700
Data Index: 7615020 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.7261. Min Act: -0.1699
Data Index: 8541643 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.7261. Min Act: -0.1700
Data Index: 5027921 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.7261. Min Act: -0.1700
Data Index: 2893043 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6636. Min Act: -0.1700
Data Index: 3455743 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6948. Min Act: -0.1700
Data Index: 2227869 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6948. Min Act: -0.1700
Data Index: 2601145 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6636. Min Act: -0.1700
Data Index: 4700055 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6323. Min Act: -0.1700
Data Index: 8278693 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6323. Min Act: -0.1700
Data Index: 4119106 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6323. Min Act: -0.1700
Data Index: 5605163 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6011. Min Act: -0.1700
Data Index: 6097362 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6323. Min Act: -0.1700
Data Index: 52754 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6323. Min Act: -0.1700
Data Index: 133885 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.5698. Min Act: -0.1700
Data Index: 4011610 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6011. Min Act: -0.1699
Data Index: 8391064 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6011. Min Act: -0.1700
Data Index: 4801370 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6011. Min Act: -0.1700
Data Index: 4228837 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7886. Min Range: -6.7886
Max Act: 6.6323. Min Act: -0.1700
Data Index: 2259487 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19