Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3984. Min Act: -0.1700
Data Index: 6289189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3984. Min Act: -0.1700
Data Index: 3619714 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3671. Min Act: -0.1700
Data Index: 6704389 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3671. Min Act: -0.1700
Data Index: 5151007 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3359. Min Act: -0.1700
Data Index: 157475 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3359. Min Act: -0.1700
Data Index: 7884237 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3359. Min Act: -0.1700
Data Index: 420113 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 5762200 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 442826 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 5597909 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 5446932 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 792855 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 3125305 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 3641203 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.3046. Min Act: -0.1700
Data Index: 905584 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.2734. Min Act: -0.1700
Data Index: 5310731 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.2734. Min Act: -0.1700
Data Index: 1959587 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.2734. Min Act: -0.1700
Data Index: 1098459 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.2734. Min Act: -0.1700
Data Index: 3282961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3984. Min Range: -4.3984
Max Act: 4.2734. Min Act: -0.1700
Data Index: 5137544 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19