Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1349 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.8935. Min Act: -0.1700
Data Index: 8779675 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.8935. Min Act: -0.1700
Data Index: 3542584 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.8935. Min Act: -0.1700
Data Index: 1067230 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.7998. Min Act: -0.1700
Data Index: 5687023 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.8623. Min Act: -0.1700
Data Index: 7635959 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.7685. Min Act: -0.1700
Data Index: 4623577 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.7685. Min Act: -0.1700
Data Index: 5691229 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.6435. Min Act: -0.1700
Data Index: 7297893 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.5810. Min Act: -0.1700
Data Index: 1839826 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.6123. Min Act: -0.1700
Data Index: 1417594 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.6123. Min Act: -0.1700
Data Index: 13031 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.5185. Min Act: -0.1700
Data Index: 7910531 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.5810. Min Act: -0.1700
Data Index: 3917343 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.5810. Min Act: -0.1700
Data Index: 1536085 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.6435. Min Act: -0.1700
Data Index: 3934716 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.6123. Min Act: -0.1700
Data Index: 3157283 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.6123. Min Act: -0.1700
Data Index: 2358101 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2910438 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.5185. Min Act: -0.1700
Data Index: 6376716 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8935. Min Range: -5.8935
Max Act: 5.5810. Min Act: -0.1700
Data Index: 7312089 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19