Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 721562 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 8300503 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 4022648 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3978. Min Act: -0.1700
Data Index: 7012110 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 4602596 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 5480526 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3353. Min Act: -0.1700
Data Index: 5455408 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3040. Min Act: -0.1700
Data Index: 5455401 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2728. Min Act: -0.1700
Data Index: 3696932 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2728. Min Act: -0.1700
Data Index: 3303858 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2728. Min Act: -0.1700
Data Index: 1460891 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2415. Min Act: -0.1700
Data Index: 4243546 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2728. Min Act: -0.1700
Data Index: 6752872 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2415. Min Act: -0.1700
Data Index: 1969108 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2415. Min Act: -0.1700
Data Index: 8827045 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2415. Min Act: -0.1700
Data Index: 481728 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2103. Min Act: -0.1700
Data Index: 632646 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2103. Min Act: -0.1700
Data Index: 840908 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.2103. Min Act: -0.1700
Data Index: 2494219 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.1790. Min Act: -0.1700
Data Index: 1074447 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19