Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.4467. Min Act: -0.1700
Data Index: 109441 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.3217. Min Act: -0.1700
Data Index: 8070709 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.3217. Min Act: -0.1700
Data Index: 6380137 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1967. Min Act: -0.1700
Data Index: 6992171 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1967. Min Act: -0.1700
Data Index: 874245 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1967. Min Act: -0.1700
Data Index: 8699229 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1654. Min Act: -0.1700
Data Index: 1888875 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1654. Min Act: -0.1700
Data Index: 110446 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1342. Min Act: -0.1700
Data Index: 1483323 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0717. Min Act: -0.1700
Data Index: 8673224 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0717. Min Act: -0.1700
Data Index: 1643982 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1029. Min Act: -0.1700
Data Index: 8347639 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0717. Min Act: -0.1700
Data Index: 4453858 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.1029. Min Act: -0.1700
Data Index: 3802590 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0404. Min Act: -0.1700
Data Index: 2066836 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0717. Min Act: -0.1700
Data Index: 4395464 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0092. Min Act: -0.1700
Data Index: 6648459 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0717. Min Act: -0.1700
Data Index: 1057168 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0404. Min Act: -0.1700
Data Index: 7697347 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4467. Min Range: -6.4467
Max Act: 6.0092. Min Act: -0.1700
Data Index: 3451995 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19