Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.1928. Min Act: -0.1700
Data Index: 7317094 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.1303. Min Act: -0.1700
Data Index: 5614530 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.0678. Min Act: -0.1700
Data Index: 207694 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.0678. Min Act: -0.1700
Data Index: 8310011 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.0678. Min Act: -0.1700
Data Index: 5625034 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.0365. Min Act: -0.1700
Data Index: 5300896 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.0365. Min Act: -0.1700
Data Index: 679793 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.0053. Min Act: -0.1700
Data Index: 6548166 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1928. Min Range: -6.1928
Max Act: 6.0365. Min Act: -0.1700
Data Index: 3603238 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9740. Min Act: -0.1700
Data Index: 4248905 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9428. Min Act: -0.1700
Data Index: 7616472 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9740. Min Act: -0.1700
Data Index: 2835276 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9428. Min Act: -0.1700
Data Index: 452532 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9428. Min Act: -0.1700
Data Index: 6478472 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.8803. Min Act: -0.1700
Data Index: 1162022 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9115. Min Act: -0.1700
Data Index: 2819152 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9115. Min Act: -0.1700
Data Index: 2507839 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9115. Min Act: -0.1700
Data Index: 8395519 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9115. Min Act: -0.1700
Data Index: 2915036 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1928. Min Range: -6.1928
Max Act: 5.9115. Min Act: -0.1700
Data Index: 4324409 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19