Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4582 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.2886. Min Act: -0.1700
Data Index: 1340363 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.2574. Min Act: -0.1700
Data Index: 1898991 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.2261. Min Act: -0.1700
Data Index: 1680039 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1636. Min Act: -0.1700
Data Index: 6148696 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1636. Min Act: -0.1700
Data Index: 6291526 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1324. Min Act: -0.1700
Data Index: 8729276 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1636. Min Act: -0.1700
Data Index: 8734920 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1636. Min Act: -0.1700
Data Index: 197297 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1324. Min Act: -0.1700
Data Index: 6962020 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1324. Min Act: -0.1700
Data Index: 2718583 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1324. Min Act: -0.1700
Data Index: 2470710 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1011. Min Act: -0.1700
Data Index: 2176600 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.1011. Min Act: -0.1700
Data Index: 297853 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.0699. Min Act: -0.1700
Data Index: 4433535 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.0699. Min Act: -0.1700
Data Index: 7921063 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.0386. Min Act: -0.1700
Data Index: 5995549 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.0386. Min Act: -0.1700
Data Index: 2978337 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.0386. Min Act: -0.1700
Data Index: 1651111 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.0073. Min Act: -0.1700
Data Index: 4087905 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2886. Min Range: -4.2886
Max Act: 4.0073. Min Act: -0.1700
Data Index: 7169178 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19