Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1903. Min Range: -7.1903
Max Act: 7.1903. Min Act: -0.1700
Data Index: 5143730 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.5340. Min Act: -0.1700
Data Index: 7061945 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.5028. Min Act: -0.1700
Data Index: 8804905 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.4403. Min Act: -0.1700
Data Index: 4357694 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.4403. Min Act: -0.1700
Data Index: 102453 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.4090. Min Act: -0.1700
Data Index: 3362606 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.2840. Min Act: -0.1700
Data Index: 2456045 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.2215. Min Act: -0.1700
Data Index: 5000930 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.2215. Min Act: -0.1700
Data Index: 7345091 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.2215. Min Act: -0.1700
Data Index: 1641359 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.1903. Min Act: -0.1700
Data Index: 2486598 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.1903. Min Act: -0.1700
Data Index: 6005820 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.1278. Min Act: -0.1700
Data Index: 2588482 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.1278. Min Act: -0.1700
Data Index: 801544 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.1590. Min Act: -0.1700
Data Index: 5207303 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.0965. Min Act: -0.1700
Data Index: 2562289 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.0653. Min Act: -0.1700
Data Index: 7444197 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.0653. Min Act: -0.1700
Data Index: 1481569 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.0653. Min Act: -0.1700
Data Index: 2414947 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1903. Min Range: -7.1903
Max Act: 6.0653. Min Act: -0.1700
Data Index: 4638132 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19