Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2487 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4403. Min Act: -0.1700
Data Index: 3846901 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4403. Min Act: -0.1700
Data Index: 1020948 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4403. Min Act: -0.1700
Data Index: 1020945 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6856894 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3534372 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4090. Min Act: -0.1700
Data Index: 1020946 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4090. Min Act: -0.1700
Data Index: 616927 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4090. Min Act: -0.1700
Data Index: 1020939 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4090. Min Act: -0.1700
Data Index: 4375731 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.4090. Min Act: -0.1700
Data Index: 1020940 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.3778. Min Act: -0.1700
Data Index: 1020943 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.3153. Min Act: -0.1700
Data Index: 641890 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.3153. Min Act: -0.1700
Data Index: 6345010 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.3153. Min Act: -0.1700
Data Index: 755847 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.3153. Min Act: -0.1700
Data Index: 5085002 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.3153. Min Act: -0.1700
Data Index: 8228884 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.3153. Min Act: -0.1692
Data Index: 7742329 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.2840. Min Act: -0.1700
Data Index: 1020942 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.2840. Min Act: -0.1700
Data Index: 209433 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4715. Min Range: -5.4715
Max Act: 5.2528. Min Act: -0.1700
Data Index: 4518089 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19