Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0256. Min Range: -8.0256
Max Act: 8.0256. Min Act: -0.1700
Data Index: 3816310 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.4631. Min Act: -0.1700
Data Index: 6883703 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.3694. Min Act: -0.1700
Data Index: 7732740 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.3381. Min Act: -0.1700
Data Index: 2460853 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.2756. Min Act: -0.1700
Data Index: 7525571 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.2444. Min Act: -0.1700
Data Index: 3801628 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.1819. Min Act: -0.1700
Data Index: 1951223 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.1506. Min Act: -0.1700
Data Index: 3523932 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.1506. Min Act: -0.1700
Data Index: 1410310 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0256. Min Range: -8.0256
Max Act: 7.0569. Min Act: -0.1700
Data Index: 8575080 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.9319. Min Act: -0.1700
Data Index: 5492345 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.9631. Min Act: -0.1700
Data Index: 5892074 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.9631. Min Act: -0.1700
Data Index: 3765537 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.9319. Min Act: -0.1700
Data Index: 4855901 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.9006. Min Act: -0.1700
Data Index: 5600452 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.9006. Min Act: -0.1700
Data Index: 5506528 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.8694. Min Act: -0.1700
Data Index: 5258142 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.8694. Min Act: -0.1700
Data Index: 6200538 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.8694. Min Act: -0.1700
Data Index: 5071658 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0256. Min Range: -8.0256
Max Act: 6.8694. Min Act: -0.1700
Data Index: 6423532 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19