Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.4370. Min Act: -0.1700
Data Index: 7760056 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.3745. Min Act: -0.1700
Data Index: 1682135 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.3433. Min Act: -0.1700
Data Index: 631412 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.2495. Min Act: -0.1700
Data Index: 2406891 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.1870. Min Act: -0.1700
Data Index: 4374529 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.1870. Min Act: -0.1700
Data Index: 2282149 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.1870. Min Act: -0.1700
Data Index: 2425886 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.1245. Min Act: -0.1700
Data Index: 1309372 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.1558. Min Act: -0.1700
Data Index: 2655235 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.1245. Min Act: -0.1700
Data Index: 5577789 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.1558. Min Act: -0.1700
Data Index: 6454574 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4370. Min Range: -7.4370
Max Act: 7.0620. Min Act: -0.1700
Data Index: 755680 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9995. Min Act: -0.1700
Data Index: 4683175 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9995. Min Act: -0.1700
Data Index: 8568904 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9370. Min Act: -0.1700
Data Index: 8365571 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9683. Min Act: -0.1700
Data Index: 3023624 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9370. Min Act: -0.1700
Data Index: 6574585 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9058. Min Act: -0.1700
Data Index: 6690800 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9058. Min Act: -0.1700
Data Index: 7330808 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4370. Min Range: -7.4370
Max Act: 6.9058. Min Act: -0.1700
Data Index: 1738734 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19