Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4482. Min Range: -10.4482
Max Act: 10.4482. Min Act: -0.1700
Data Index: 4842659 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.8857. Min Act: -0.1700
Data Index: 5384560 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.7607. Min Act: -0.1700
Data Index: 59939 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.6982. Min Act: -0.1700
Data Index: 1862301 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.6982. Min Act: -0.1700
Data Index: 4816546 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.6357. Min Act: -0.1700
Data Index: 8578948 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.6357. Min Act: -0.1700
Data Index: 8748860 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5732. Min Act: -0.1700
Data Index: 2222768 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5732. Min Act: -0.1700
Data Index: 5348622 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5107. Min Act: -0.1700
Data Index: 2864952 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5107. Min Act: -0.1700
Data Index: 8090154 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5732. Min Act: -0.1700
Data Index: 6528782 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5107. Min Act: -0.1700
Data Index: 8471845 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5107. Min Act: -0.1700
Data Index: 2033829 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.4482. Min Act: -0.1700
Data Index: 4563444 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.3857. Min Act: -0.1700
Data Index: 3613503 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.4482. Min Act: -0.1700
Data Index: 8222031 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.4482. Min Act: -0.1700
Data Index: 1185394 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.5107. Min Act: -0.1700
Data Index: 6568260 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4482. Min Range: -10.4482
Max Act: 9.3857. Min Act: -0.1700
Data Index: 5541363 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19