Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4556 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.2611. Min Act: -0.1700
Data Index: 4488267 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2611. Min Range: -5.2611
Max Act: 5.0111. Min Act: -0.1700
Data Index: 5678662 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.9173. Min Act: -0.1700
Data Index: 2130616 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8861. Min Act: -0.1700
Data Index: 5794592 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8548. Min Act: -0.1700
Data Index: 7382085 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.8236. Min Act: -0.1700
Data Index: 8607623 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.7923. Min Act: -0.1700
Data Index: 3939059 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.7611. Min Act: -0.1700
Data Index: 1806155 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.7298. Min Act: -0.1700
Data Index: 5562292 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.6673. Min Act: -0.1700
Data Index: 7555174 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.6673. Min Act: -0.1700
Data Index: 2552447 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.6673. Min Act: -0.1700
Data Index: 2087232 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.6361. Min Act: -0.1700
Data Index: 7602015 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.6361. Min Act: -0.1700
Data Index: 2504745 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.6048. Min Act: -0.1700
Data Index: 5091890 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.5736. Min Act: -0.1700
Data Index: 1994138 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.5736. Min Act: -0.1700
Data Index: 5502531 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.5423. Min Act: -0.1700
Data Index: 3894711 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.5423. Min Act: -0.1700
Data Index: 5810395 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2611. Min Range: -5.2611
Max Act: 4.5111. Min Act: -0.1700
Data Index: 8020577 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19