Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1114 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3948. Min Range: -6.3948
Max Act: 6.3948. Min Act: -0.1700
Data Index: 75796 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.7385. Min Act: -0.1700
Data Index: 3589021 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.6448. Min Act: -0.1700
Data Index: 4332922 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.6448. Min Act: -0.1700
Data Index: 595292 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.6135. Min Act: -0.1700
Data Index: 3203038 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.5510. Min Act: -0.1700
Data Index: 8081677 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.4885. Min Act: -0.1700
Data Index: 6529215 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.4573. Min Act: -0.1700
Data Index: 7142135 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.4885. Min Act: -0.1700
Data Index: 2013206 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.4260. Min Act: -0.1700
Data Index: 1903930 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.4573. Min Act: -0.1700
Data Index: 7384118 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.4260. Min Act: -0.1700
Data Index: 1460509 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 5554986 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.4260. Min Act: -0.1700
Data Index: 7289703 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.3635. Min Act: -0.1700
Data Index: 8189987 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.3635. Min Act: -0.1700
Data Index: 4527899 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.3323. Min Act: -0.1700
Data Index: 968330 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 7826112 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.3635. Min Act: -0.1700
Data Index: 428972 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.3635. Min Act: -0.1700
Data Index: 8670233 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19