Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2736. Min Range: -8.2736
Max Act: 8.2736. Min Act: -0.1700
Data Index: 3313064 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2736. Min Range: -8.2736
Max Act: 8.2111. Min Act: -0.1700
Data Index: 2992623 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.8673. Min Act: -0.1700
Data Index: 6925842 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.6173. Min Act: -0.1700
Data Index: 6683386 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.6486. Min Act: -0.1700
Data Index: 6950071 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.5236. Min Act: -0.1700
Data Index: 2403525 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.4611. Min Act: -0.1700
Data Index: 2493636 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.4611. Min Act: -0.1700
Data Index: 42391 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.3986. Min Act: -0.1700
Data Index: 2992629 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.2736. Min Act: -0.1700
Data Index: 6841398 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.2736. Min Act: -0.1700
Data Index: 3527665 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.2423. Min Act: -0.1700
Data Index: 2046160 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.1486. Min Act: -0.1700
Data Index: 1399279 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.1486. Min Act: -0.1700
Data Index: 975682 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.1173. Min Act: -0.1700
Data Index: 2979412 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.0861. Min Act: -0.1700
Data Index: 1741428 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.0548. Min Act: -0.1700
Data Index: 7719834 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.0548. Min Act: -0.1700
Data Index: 7804828 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.1173. Min Act: -0.1700
Data Index: 8698899 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2736. Min Range: -8.2736
Max Act: 7.0236. Min Act: -0.1700
Data Index: 2183451 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19