Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.7553. Min Act: -0.1700
Data Index: 6618403 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.7553. Min Act: -0.1700
Data Index: 1792657 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.6616. Min Act: -0.1700
Data Index: 5497025 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.6303. Min Act: -0.1700
Data Index: 8030858 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.5991. Min Act: -0.1700
Data Index: 7147692 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.5678. Min Act: -0.1700
Data Index: 6087939 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.5991. Min Act: -0.1700
Data Index: 6253199 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.5678. Min Act: -0.1700
Data Index: 6267559 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.5053. Min Act: -0.1700
Data Index: 1193616 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.5053. Min Act: -0.1700
Data Index: 7565685 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.4741. Min Act: -0.1700
Data Index: 8553589 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.4741. Min Act: -0.1700
Data Index: 786092 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.4428. Min Act: -0.1700
Data Index: 8752772 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.4428. Min Act: -0.1700
Data Index: 3953945 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.4116. Min Act: -0.1700
Data Index: 1575944 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.4116. Min Act: -0.1700
Data Index: 1404273 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.3491. Min Act: -0.1700
Data Index: 6988680 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.3491. Min Act: -0.1700
Data Index: 164201 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.3491. Min Act: -0.1700
Data Index: 5229039 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7553. Min Range: -5.7553
Max Act: 5.3178. Min Act: -0.1700
Data Index: 6621055 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19