Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.6544. Min Act: -0.1700
Data Index: 828022 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.4357. Min Act: -0.1700
Data Index: 8070069 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.3419. Min Act: -0.1700
Data Index: 4339164 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.3107. Min Act: -0.1700
Data Index: 4392144 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.2794. Min Act: -0.1700
Data Index: 7509473 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.2169. Min Act: -0.1700
Data Index: 7828335 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.1857. Min Act: -0.1700
Data Index: 7645563 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.1544. Min Act: -0.1700
Data Index: 8655994 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.1232. Min Act: -0.1700
Data Index: 2738652 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.0294. Min Act: -0.1700
Data Index: 5690808 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.0607. Min Act: -0.1700
Data Index: 793895 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.0607. Min Act: -0.1700
Data Index: 1223957 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.0294. Min Act: -0.1700
Data Index: 4213666 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6544. Min Range: -7.6544
Max Act: 7.0294. Min Act: -0.1700
Data Index: 1347940 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6544. Min Range: -7.6544
Max Act: 6.9982. Min Act: -0.1700
Data Index: 7296984 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6544. Min Range: -7.6544
Max Act: 6.9982. Min Act: -0.1700
Data Index: 5017937 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6544. Min Range: -7.6544
Max Act: 6.9982. Min Act: -0.1700
Data Index: 1252241 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6544. Min Range: -7.6544
Max Act: 6.9669. Min Act: -0.1700
Data Index: 4135062 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6544. Min Range: -7.6544
Max Act: 6.9669. Min Act: -0.1700
Data Index: 7383132 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6544. Min Range: -7.6544
Max Act: 6.9669. Min Act: -0.1700
Data Index: 3321666 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19