Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 969 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.9465. Min Act: -0.1700
Data Index: 8456656 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.6965. Min Act: -0.1700
Data Index: 6259166 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.6340. Min Act: -0.1700
Data Index: 5718013 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.5715. Min Act: -0.1700
Data Index: 8297096 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.5090. Min Act: -0.1700
Data Index: 4092933 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.5090. Min Act: -0.1700
Data Index: 8120387 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.4465. Min Act: -0.1700
Data Index: 2076661 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.4778. Min Act: -0.1700
Data Index: 586252 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.4153. Min Act: -0.1700
Data Index: 1020851 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.3528. Min Act: -0.1700
Data Index: 6076908 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.3528. Min Act: -0.1700
Data Index: 3567962 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.3528. Min Act: -0.1700
Data Index: 7332802 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.3528. Min Act: -0.1700
Data Index: 1249696 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.3528. Min Act: -0.1700
Data Index: 3193290 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.2903. Min Act: -0.1700
Data Index: 2459710 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.2903. Min Act: -0.1700
Data Index: 1236920 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.2590. Min Act: -0.1700
Data Index: 6721933 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.1965. Min Act: -0.1700
Data Index: 7684854 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.1653. Min Act: -0.1700
Data Index: 8192701 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9465. Min Range: -7.9465
Max Act: 7.1028. Min Act: -0.1700
Data Index: 796696 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19