Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4609 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1362. Min Range: -6.1362
Max Act: 6.1362. Min Act: -0.1700
Data Index: 7309411 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1362. Min Range: -6.1362
Max Act: 6.0425. Min Act: -0.1700
Data Index: 1426246 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.9487. Min Act: -0.1700
Data Index: 7409874 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3234006 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.7612. Min Act: -0.1700
Data Index: 8369249 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.7300. Min Act: -0.1700
Data Index: 6789659 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.7300. Min Act: -0.1700
Data Index: 4758949 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6987. Min Act: -0.1700
Data Index: 7451597 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6675. Min Act: -0.1700
Data Index: 677626 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6675. Min Act: -0.1700
Data Index: 4631196 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6987. Min Act: -0.1700
Data Index: 6828394 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6362. Min Act: -0.1700
Data Index: 54284 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6362. Min Act: -0.1700
Data Index: 146933 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6362. Min Act: -0.1700
Data Index: 6454159 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6362. Min Act: -0.1700
Data Index: 1246957 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6050. Min Act: -0.1700
Data Index: 2130617 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6050. Min Act: -0.1700
Data Index: 7873403 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6050. Min Act: -0.1700
Data Index: 8268875 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6050. Min Act: -0.1700
Data Index: 6583495 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1362. Min Range: -6.1362
Max Act: 5.6050. Min Act: -0.1700
Data Index: 5566281 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19