Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1912. Min Range: -10.1912
Max Act: 10.1912. Min Act: -0.1700
Data Index: 2897082 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1912. Min Range: -10.1912
Max Act: 10.0662. Min Act: -0.1700
Data Index: 5733401 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.8787. Min Act: -0.1700
Data Index: 3537421 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.9412. Min Act: -0.1700
Data Index: 4665296 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.9412. Min Act: -0.1700
Data Index: 4512031 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.8162. Min Act: -0.1700
Data Index: 2212829 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.7537. Min Act: -0.1700
Data Index: 3245980 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6912. Min Act: -0.1700
Data Index: 8777409 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6287. Min Act: -0.1700
Data Index: 8588906 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6912. Min Act: -0.1700
Data Index: 2336694 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6912. Min Act: -0.1700
Data Index: 527354 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6912. Min Act: -0.1700
Data Index: 2828497 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6287. Min Act: -0.1700
Data Index: 1253590 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6287. Min Act: -0.1700
Data Index: 1897099 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.6287. Min Act: -0.1700
Data Index: 277877 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.5662. Min Act: -0.1700
Data Index: 2758877 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.5662. Min Act: -0.1700
Data Index: 4031691 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.5037. Min Act: -0.1700
Data Index: 1146798 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.5037. Min Act: -0.1700
Data Index: 3708917 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1912. Min Range: -10.1912
Max Act: 9.5662. Min Act: -0.1700
Data Index: 318899 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19