Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5259 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.5633. Min Range: -18.5633
Max Act: 18.5633. Min Act: -0.1700
Data Index: 4382260 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.5633. Min Range: -18.5633
Max Act: 18.1883. Min Act: -0.1700
Data Index: 1071691 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.5633. Min Range: -18.5633
Max Act: 18.0633. Min Act: -0.1700
Data Index: 4382258 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.5633. Min Range: -18.5633
Max Act: 18.0633. Min Act: -0.1700
Data Index: 8371644 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.5633. Min Range: -18.5633
Max Act: 18.0633. Min Act: -0.1700
Data Index: 803922 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.5633. Min Range: -18.5633
Max Act: 18.0633. Min Act: -0.1700
Data Index: 1184727 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.5633. Min Range: -18.5633
Max Act: 18.0633. Min Act: -0.1700
Data Index: 4395408 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.9383. Min Act: -0.1700
Data Index: 6355958 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.9383. Min Act: -0.1700
Data Index: 7902141 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.8133. Min Act: -0.1700
Data Index: 7928458 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.8133. Min Act: -0.1700
Data Index: 2250834 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.6883. Min Act: -0.1700
Data Index: 8434441 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.6883. Min Act: -0.1700
Data Index: 6342562 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.6883. Min Act: -0.1700
Data Index: 4796965 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.6883. Min Act: -0.1700
Data Index: 8569594 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.6883. Min Act: -0.1700
Data Index: 1787169 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.5633. Min Act: -0.1700
Data Index: 964148 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.5633. Min Act: -0.1700
Data Index: 5842698 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.4383. Min Act: -0.1700
Data Index: 6171616 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.5633. Min Range: -18.5633
Max Act: 17.5633. Min Act: -0.1700
Data Index: 1730561 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19