Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2580. Min Range: -10.2580
Max Act: 10.2580. Min Act: -0.1700
Data Index: 681546 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.9455. Min Act: -0.1700
Data Index: 5043920 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.9455. Min Act: -0.1700
Data Index: 6080729 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.9455. Min Act: -0.1700
Data Index: 2807156 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.9455. Min Act: -0.1700
Data Index: 8549164 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.8205. Min Act: -0.1699
Data Index: 4484389 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.8205. Min Act: -0.1700
Data Index: 5085108 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.7580. Min Act: -0.1700
Data Index: 4310649 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.6330. Min Act: -0.1700
Data Index: 8414659 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.5705. Min Act: -0.1700
Data Index: 863433 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.5705. Min Act: -0.1700
Data Index: 1711154 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.5080. Min Act: -0.1700
Data Index: 7771285 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.5705. Min Act: -0.1700
Data Index: 5832862 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.4455. Min Act: -0.1700
Data Index: 892524 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.4455. Min Act: -0.1700
Data Index: 1711153 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.4455. Min Act: -0.1700
Data Index: 450979 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.4455. Min Act: -0.1700
Data Index: 519837 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.4455. Min Act: -0.1700
Data Index: 1350491 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.3830. Min Act: -0.1700
Data Index: 5946892 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2580. Min Range: -10.2580
Max Act: 9.3205. Min Act: -0.1700
Data Index: 3738547 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19