Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.6801. Min Act: -0.1700
Data Index: 6579185 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5863. Min Act: -0.1700
Data Index: 8672942 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5551. Min Act: -0.1700
Data Index: 6392856 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4301. Min Act: -0.1700
Data Index: 6738452 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4301. Min Act: -0.1700
Data Index: 2295078 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3988. Min Act: -0.1700
Data Index: 2581631 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3988. Min Act: -0.1700
Data Index: 7014725 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3988. Min Act: -0.1700
Data Index: 572682 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3988. Min Act: -0.1700
Data Index: 6824628 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3988. Min Act: -0.1700
Data Index: 5377750 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3363. Min Act: -0.1700
Data Index: 3022159 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.2426. Min Act: -0.1700
Data Index: 6911993 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.2738. Min Act: -0.1700
Data Index: 8069403 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3051. Min Act: -0.1700
Data Index: 1832615 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.2738. Min Act: -0.1700
Data Index: 5591589 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.2426. Min Act: -0.1700
Data Index: 3072331 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.2113. Min Act: -0.1700
Data Index: 6692879 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1147736 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.2113. Min Act: -0.1700
Data Index: 5084870 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.1488. Min Act: -0.1700
Data Index: 4069732 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19