Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1913 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0732. Min Range: -6.0732
Max Act: 6.0732. Min Act: -0.1700
Data Index: 7302220 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0732. Min Range: -6.0732
Max Act: 6.0419. Min Act: -0.1700
Data Index: 2124936 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0732. Min Range: -6.0732
Max Act: 6.0107. Min Act: -0.1700
Data Index: 4197359 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.9794. Min Act: -0.1700
Data Index: 213973 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.9794. Min Act: -0.1700
Data Index: 6370004 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.9794. Min Act: -0.1700
Data Index: 3048002 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.9482. Min Act: -0.1700
Data Index: 8264454 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.9482. Min Act: -0.1700
Data Index: 6506964 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.9169. Min Act: -0.1700
Data Index: 2770193 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.9169. Min Act: -0.1700
Data Index: 1987105 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.8857. Min Act: -0.1700
Data Index: 8059731 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.8857. Min Act: -0.1700
Data Index: 4236207 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.8857. Min Act: -0.1700
Data Index: 4890162 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.8544. Min Act: -0.1700
Data Index: 1571892 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.8232. Min Act: -0.1700
Data Index: 7786534 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.7919. Min Act: -0.1700
Data Index: 5530773 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.8232. Min Act: -0.1700
Data Index: 2632172 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.8232. Min Act: -0.1700
Data Index: 4816256 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.7919. Min Act: -0.1700
Data Index: 3962144 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0732. Min Range: -6.0732
Max Act: 5.7919. Min Act: -0.1700
Data Index: 785849 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19