Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2061 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6847. Min Range: -8.6847
Max Act: 8.6847. Min Act: -0.1700
Data Index: 1417653 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6847. Min Range: -8.6847
Max Act: 8.1847. Min Act: -0.1700
Data Index: 3348162 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6847. Min Range: -8.6847
Max Act: 8.0597. Min Act: -0.1700
Data Index: 2679156 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.9972. Min Act: -0.1700
Data Index: 4389997 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6847. Min Range: -8.6847
Max Act: 8.0284. Min Act: -0.1700
Data Index: 3750576 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.9347. Min Act: -0.1700
Data Index: 1680825 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.9034. Min Act: -0.1700
Data Index: 689369 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.8097. Min Act: -0.1700
Data Index: 6213075 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.8097. Min Act: -0.1700
Data Index: 5383609 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.6847. Min Act: -0.1700
Data Index: 4387839 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.5909. Min Act: -0.1700
Data Index: 8741301 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4972. Min Act: -0.1700
Data Index: 5383610 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4972. Min Act: -0.1700
Data Index: 597238 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4347. Min Act: -0.1700
Data Index: 8627666 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4347. Min Act: -0.1700
Data Index: 1810301 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4347. Min Act: -0.1700
Data Index: 4935031 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4347. Min Act: -0.1700
Data Index: 1675992 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4347. Min Act: -0.1700
Data Index: 161300 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4034. Min Act: -0.1700
Data Index: 4087520 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6847. Min Range: -8.6847
Max Act: 7.4034. Min Act: -0.1700
Data Index: 5493324 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19