Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.8602. Min Act: -0.1700
Data Index: 8161874 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.8602. Min Act: -0.1700
Data Index: 6822768 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7977. Min Act: -0.1700
Data Index: 958620 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7665. Min Act: -0.1700
Data Index: 608327 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7977. Min Act: -0.1700
Data Index: 4150859 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7352. Min Act: -0.1700
Data Index: 2940189 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7352. Min Act: -0.1700
Data Index: 2508366 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7352. Min Act: -0.1700
Data Index: 5784997 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7352. Min Act: -0.1700
Data Index: 2416374 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7352. Min Act: -0.1700
Data Index: 245858 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7352. Min Act: -0.1700
Data Index: 579608 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7040. Min Act: -0.1700
Data Index: 3840011 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7040. Min Act: -0.1700
Data Index: 3639042 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7040. Min Act: -0.1700
Data Index: 8290902 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.6727. Min Act: -0.1700
Data Index: 8132688 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.7040. Min Act: -0.1700
Data Index: 1808103 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.6415. Min Act: -0.1700
Data Index: 3776533 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.6415. Min Act: -0.1700
Data Index: 3268321 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.6415. Min Act: -0.1700
Data Index: 8255791 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8602. Min Range: -5.8602
Max Act: 5.6102. Min Act: -0.1700
Data Index: 4356818 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19