Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2787. Min Range: -10.2787
Max Act: 10.2787. Min Act: -0.1700
Data Index: 2039606 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2787. Min Range: -10.2787
Max Act: 10.0287. Min Act: -0.1700
Data Index: 8499503 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.9662. Min Act: -0.1700
Data Index: 5396380 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.9662. Min Act: -0.1700
Data Index: 6683284 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.9037. Min Act: -0.1700
Data Index: 5325564 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.9662. Min Act: -0.1700
Data Index: 8295554 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.9037. Min Act: -0.1700
Data Index: 2187938 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.8412. Min Act: -0.1700
Data Index: 7549184 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.8412. Min Act: -0.1700
Data Index: 4423392 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.8412. Min Act: -0.1700
Data Index: 2772963 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.8412. Min Act: -0.1700
Data Index: 2329196 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.8412. Min Act: -0.1700
Data Index: 4900664 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.7162. Min Act: -0.1700
Data Index: 5599186 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.8412. Min Act: -0.1700
Data Index: 8323865 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.7787. Min Act: -0.1700
Data Index: 7563526 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.7787. Min Act: -0.1700
Data Index: 7249553 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.7162. Min Act: -0.1700
Data Index: 1835105 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.7162. Min Act: -0.1700
Data Index: 315247 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.7162. Min Act: -0.1700
Data Index: 7865510 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2787. Min Range: -10.2787
Max Act: 9.6537. Min Act: -0.1700
Data Index: 5000070 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19