Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.9918. Min Act: -0.1700
Data Index: 5614815 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3382442 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8981. Min Act: -0.1700
Data Index: 378589 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.9293. Min Act: -0.1700
Data Index: 4273537 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.9293. Min Act: -0.1700
Data Index: 1532182 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8981. Min Act: -0.1700
Data Index: 637707 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8981. Min Act: -0.1700
Data Index: 5859655 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8981. Min Act: -0.1700
Data Index: 5965675 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8981. Min Act: -0.1700
Data Index: 3015674 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8668. Min Act: -0.1700
Data Index: 1549479 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8668. Min Act: -0.1700
Data Index: 1846445 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8356. Min Act: -0.1700
Data Index: 1100008 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8668. Min Act: -0.1700
Data Index: 2839220 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8668. Min Act: -0.1700
Data Index: 7567024 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8668. Min Act: -0.1700
Data Index: 1071643 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8356. Min Act: -0.1700
Data Index: 6956977 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8356. Min Act: -0.1700
Data Index: 7950436 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8043. Min Act: -0.1700
Data Index: 5656850 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8043. Min Act: -0.1700
Data Index: 6169969 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9918. Min Range: -5.9918
Max Act: 5.8043. Min Act: -0.1700
Data Index: 7099658 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19