Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 773 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1708. Min Range: -4.1708
Max Act: 4.1708. Min Act: -0.1700
Data Index: 3443094 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1708. Min Range: -4.1708
Max Act: 4.0458. Min Act: -0.1700
Data Index: 8632082 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.9833. Min Act: -0.1700
Data Index: 8582825 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.9520. Min Act: -0.1700
Data Index: 3007457 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.9520. Min Act: -0.1700
Data Index: 4296658 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8582. Min Act: -0.1700
Data Index: 8582824 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8895. Min Act: -0.1700
Data Index: 7451530 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8895. Min Act: -0.1700
Data Index: 5540357 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8582. Min Act: -0.1700
Data Index: 6662920 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8582. Min Act: -0.1700
Data Index: 3251363 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.7957. Min Act: -0.1700
Data Index: 3542470 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8270. Min Act: -0.1700
Data Index: 3716884 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8582. Min Act: -0.1700
Data Index: 2162758 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8270. Min Act: -0.1700
Data Index: 6662922 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8270. Min Act: -0.1700
Data Index: 6834696 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.8270. Min Act: -0.1700
Data Index: 8635708 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.7957. Min Act: -0.1700
Data Index: 3190451 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.7957. Min Act: -0.1700
Data Index: 1953907 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.7644. Min Act: -0.1700
Data Index: 5616687 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1708. Min Range: -4.1708
Max Act: 3.7644. Min Act: -0.1700
Data Index: 5580675 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19