Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.5997. Min Act: -0.1700
Data Index: 4603125 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.2560. Min Act: -0.1700
Data Index: 7501521 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.2247. Min Act: -0.1700
Data Index: 142586 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.2247. Min Act: -0.1700
Data Index: 3821703 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.1935. Min Act: -0.1700
Data Index: 7135922 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.1935. Min Act: -0.1700
Data Index: 3026335 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.1622. Min Act: -0.1700
Data Index: 2466358 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.1622. Min Act: -0.1700
Data Index: 5906855 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.1622. Min Act: -0.1700
Data Index: 3190185 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0997. Min Act: -0.1700
Data Index: 5906864 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0685. Min Act: -0.1700
Data Index: 699125 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0685. Min Act: -0.1700
Data Index: 8448936 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0685. Min Act: -0.1700
Data Index: 869014 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0060. Min Act: -0.1700
Data Index: 354031 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0372. Min Act: -0.1700
Data Index: 138009 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0060. Min Act: -0.1700
Data Index: 4883162 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0060. Min Act: -0.1700
Data Index: 7038182 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5997. Min Range: -6.5997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 5824782 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5997. Min Range: -6.5997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 5710614 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5997. Min Range: -6.5997
Max Act: 6.0060. Min Act: -0.1700
Data Index: 6758790 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19