Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2477 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.4403. Min Act: -0.1700
Data Index: 1532299 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.3778. Min Act: -0.1700
Data Index: 69745 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.2841. Min Act: -0.1700
Data Index: 8810857 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.1591. Min Act: -0.1700
Data Index: 6836920 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.1278. Min Act: -0.1700
Data Index: 8478691 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.1278. Min Act: -0.1700
Data Index: 2896740 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.0966. Min Act: -0.1700
Data Index: 7018493 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.0966. Min Act: -0.1700
Data Index: 5738661 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.0653. Min Act: -0.1700
Data Index: 3010469 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.0341. Min Act: -0.1700
Data Index: 7674129 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4403. Min Range: -7.4403
Max Act: 7.0028. Min Act: -0.1700
Data Index: 5185404 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9716. Min Act: -0.1700
Data Index: 7880782 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9403. Min Act: -0.1700
Data Index: 3933525 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9091. Min Act: -0.1700
Data Index: 4853149 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9403. Min Act: -0.1700
Data Index: 6625440 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9403. Min Act: -0.1700
Data Index: 3871950 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9403. Min Act: -0.1700
Data Index: 1582046 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9091. Min Act: -0.1700
Data Index: 433482 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9091. Min Act: -0.1700
Data Index: 4326254 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4403. Min Range: -7.4403
Max Act: 6.9091. Min Act: -0.1700
Data Index: 2885299 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19