Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.4609. Min Act: -0.1700
Data Index: 5512605 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.3984. Min Act: -0.1700
Data Index: 7142352 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.2109. Min Act: -0.1700
Data Index: 567871 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.1484. Min Act: -0.1700
Data Index: 7611444 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.2109. Min Act: -0.1700
Data Index: 1242566 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.0859. Min Act: -0.1700
Data Index: 2778936 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.0234. Min Act: -0.1700
Data Index: 7818233 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4609. Min Range: -9.4609
Max Act: 9.0234. Min Act: -0.1700
Data Index: 7818217 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.9609. Min Act: -0.1700
Data Index: 6448293 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.9609. Min Act: -0.1700
Data Index: 5619444 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.9609. Min Act: -0.1700
Data Index: 8267350 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.8359. Min Act: -0.1700
Data Index: 6247752 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.8984. Min Act: -0.1700
Data Index: 7456356 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.8984. Min Act: -0.1700
Data Index: 7394495 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.9609. Min Act: -0.1700
Data Index: 3839273 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.8984. Min Act: -0.1700
Data Index: 6742804 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.8984. Min Act: -0.1700
Data Index: 1028844 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.7734. Min Act: -0.1700
Data Index: 4029667 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.8359. Min Act: -0.1700
Data Index: 5709894 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4609. Min Range: -9.4609
Max Act: 8.8359. Min Act: -0.1700
Data Index: 1653988 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19