Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4116 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.3555. Min Act: -0.1700
Data Index: 6097490 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.2930. Min Act: -0.1700
Data Index: 6516640 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1680. Min Act: -0.1700
Data Index: 5396770 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.2305. Min Act: -0.1700
Data Index: 6056805 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1993. Min Act: -0.1700
Data Index: 4479970 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.2305. Min Act: -0.1700
Data Index: 5760733 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1993. Min Act: -0.1700
Data Index: 5395064 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1680. Min Act: -0.1700
Data Index: 7282992 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1680. Min Act: -0.1700
Data Index: 5407012 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1368. Min Act: -0.1700
Data Index: 4219220 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1368. Min Act: -0.1700
Data Index: 394479 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.1055. Min Act: -0.1700
Data Index: 817946 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.0743. Min Act: -0.1700
Data Index: 2255691 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.0743. Min Act: -0.1700
Data Index: 7112773 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.0743. Min Act: -0.1700
Data Index: 4731978 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.0743. Min Act: -0.1700
Data Index: 5167622 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.0118. Min Act: -0.1700
Data Index: 8355071 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.0430. Min Act: -0.1700
Data Index: 2996394 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3555. Min Range: -6.3555
Max Act: 6.0118. Min Act: -0.1700
Data Index: 1667794 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3555. Min Range: -6.3555
Max Act: 5.9805. Min Act: -0.1700
Data Index: 7400467 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19