Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.6525. Min Act: -0.1700
Data Index: 2872848 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.4025. Min Act: -0.1700
Data Index: 1849337 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.3712. Min Act: -0.1700
Data Index: 5427490 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.3712. Min Act: -0.1700
Data Index: 4855554 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.3087. Min Act: -0.1700
Data Index: 4691555 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.2775. Min Act: -0.1700
Data Index: 2517307 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.2775. Min Act: -0.1700
Data Index: 7620099 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.2462. Min Act: -0.1700
Data Index: 6872795 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.2150. Min Act: -0.1700
Data Index: 4691553 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.2150. Min Act: -0.1700
Data Index: 1943581 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.2150. Min Act: -0.1700
Data Index: 6568079 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.1837. Min Act: -0.1700
Data Index: 6143071 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.1525. Min Act: -0.1700
Data Index: 7384260 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.1525. Min Act: -0.1700
Data Index: 6033280 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.1525. Min Act: -0.1700
Data Index: 5713910 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.1525. Min Act: -0.1700
Data Index: 871698 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.1525. Min Act: -0.1700
Data Index: 5633265 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.1212. Min Act: -0.1700
Data Index: 3570634 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.0900. Min Act: -0.1700
Data Index: 6326338 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6525. Min Range: -5.6525
Max Act: 5.0900. Min Act: -0.1700
Data Index: 1074026 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19