Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1497 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1636. Min Range: -12.1636
Max Act: 12.1636. Min Act: -0.1700
Data Index: 4809960 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.8511. Min Act: -0.1700
Data Index: 5617785 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.7886. Min Act: -0.1700
Data Index: 8675426 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.6011. Min Act: -0.1700
Data Index: 3328869 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.6011. Min Act: -0.1700
Data Index: 693357 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.6011. Min Act: -0.1700
Data Index: 6565266 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.4136. Min Act: -0.1700
Data Index: 3678474 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.3511. Min Act: -0.1700
Data Index: 7006652 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.3511. Min Act: -0.1700
Data Index: 7349335 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.2886. Min Act: -0.1700
Data Index: 6565261 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.3511. Min Act: -0.1700
Data Index: 7885481 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.2886. Min Act: -0.1700
Data Index: 4465107 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.1636. Min Act: -0.1700
Data Index: 114128 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.1011. Min Act: -0.1700
Data Index: 5532704 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.1011. Min Act: -0.1700
Data Index: 2603573 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.0386. Min Act: -0.1700
Data Index: 6424580 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1636. Min Range: -12.1636
Max Act: 11.0386. Min Act: -0.1700
Data Index: 8217997 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1636. Min Range: -12.1636
Max Act: 10.9761. Min Act: -0.1700
Data Index: 8062610 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1636. Min Range: -12.1636
Max Act: 10.9761. Min Act: -0.1700
Data Index: 1645019 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1636. Min Range: -12.1636
Max Act: 10.9136. Min Act: -0.1700
Data Index: 6579835 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19