Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 2294923 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 5344707 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.7736. Min Act: -0.1700
Data Index: 2066640 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.7423. Min Act: -0.1700
Data Index: 3382243 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.7111. Min Act: -0.1700
Data Index: 2482335 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.6798. Min Act: -0.1700
Data Index: 5562784 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5861. Min Act: -0.1700
Data Index: 2890385 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5861. Min Act: -0.1700
Data Index: 5778224 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5548. Min Act: -0.1700
Data Index: 5581691 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5548. Min Act: -0.1700
Data Index: 8492577 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2239608 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5548. Min Act: -0.1700
Data Index: 6424469 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5236. Min Act: -0.1700
Data Index: 7415833 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.4923. Min Act: -0.1700
Data Index: 5515368 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5236. Min Act: -0.1700
Data Index: 3949622 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5236. Min Act: -0.1700
Data Index: 3803644 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5548. Min Act: -0.1700
Data Index: 5307313 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.5236. Min Act: -0.1700
Data Index: 3167267 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.4611. Min Act: -0.1700
Data Index: 5704583 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8048. Min Range: -5.8048
Max Act: 5.4923. Min Act: -0.1700
Data Index: 6476751 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19