Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.9349. Min Act: -0.1700
Data Index: 1155852 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.7785. Min Act: -0.1700
Data Index: 4029738 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.5908. Min Act: -0.1700
Data Index: 3195990 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.5282. Min Act: -0.1700
Data Index: 3296717 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.5595. Min Act: -0.1700
Data Index: 7580535 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.5282. Min Act: -0.1700
Data Index: 8293404 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.4655. Min Act: -0.1700
Data Index: 259626 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.4185. Min Act: -0.1700
Data Index: 5638600 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.4028. Min Act: -0.1700
Data Index: 615243 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3715. Min Act: -0.1700
Data Index: 2482655 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3715. Min Act: -0.1700
Data Index: 5321754 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3401. Min Act: -0.1700
Data Index: 797362 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3244. Min Act: -0.1700
Data Index: 2344720 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3087. Min Act: -0.1700
Data Index: 6226508 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3087. Min Act: -0.1700
Data Index: 1868412 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3087. Min Act: -0.1700
Data Index: 6871020 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.3087. Min Act: -0.1700
Data Index: 7588484 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.2930. Min Act: -0.1700
Data Index: 8249018 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.2773. Min Act: -0.1700
Data Index: 3204790 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9349. Min Range: -3.9349
Max Act: 3.2930. Min Act: -0.1700
Data Index: 4310799 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19