Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 483 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.7744. Min Act: -0.1700
Data Index: 6906794 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.7432. Min Act: -0.1700
Data Index: 107582 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.7432. Min Act: -0.1700
Data Index: 1782970 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.6807. Min Act: -0.1700
Data Index: 2533227 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.6807. Min Act: -0.1700
Data Index: 7330308 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.6494. Min Act: -0.1700
Data Index: 7551782 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.6494. Min Act: -0.1700
Data Index: 3747372 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.6182. Min Act: -0.1700
Data Index: 4823139 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5869. Min Act: -0.1700
Data Index: 2977919 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5557. Min Act: -0.1700
Data Index: 4604115 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5869. Min Act: -0.1700
Data Index: 4229473 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5869. Min Act: -0.1700
Data Index: 711480 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5869. Min Act: -0.1700
Data Index: 6924373 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5869. Min Act: -0.1700
Data Index: 8281488 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5557. Min Act: -0.1700
Data Index: 7970213 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5557. Min Act: -0.1700
Data Index: 4952331 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5869. Min Act: -0.1700
Data Index: 2664407 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4932. Min Act: -0.1700
Data Index: 443635 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5244. Min Act: -0.1700
Data Index: 2764172 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5557. Min Act: -0.1700
Data Index: 646119 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19