Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.7383. Min Act: -0.1700
Data Index: 5539980 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.5196. Min Act: -0.1700
Data Index: 3496585 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3946. Min Act: -0.1700
Data Index: 6868731 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3633. Min Act: -0.1700
Data Index: 4582761 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3633. Min Act: -0.1700
Data Index: 7302933 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3946. Min Act: -0.1700
Data Index: 7091402 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3321. Min Act: -0.1700
Data Index: 7509282 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3321. Min Act: -0.1700
Data Index: 3110897 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3321. Min Act: -0.1700
Data Index: 3163780 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3008. Min Act: -0.1700
Data Index: 6311488 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3008. Min Act: -0.1700
Data Index: 4716590 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3008. Min Act: -0.1700
Data Index: 8126444 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3008. Min Act: -0.1700
Data Index: 5611650 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3008. Min Act: -0.1700
Data Index: 2046077 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2696. Min Act: -0.1700
Data Index: 3650338 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2696. Min Act: -0.1700
Data Index: 868328 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2696. Min Act: -0.1700
Data Index: 2076488 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2696. Min Act: -0.1700
Data Index: 1086534 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2696. Min Act: -0.1700
Data Index: 2878841 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2696. Min Act: -0.1700
Data Index: 1703149 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19