Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 775 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2248. Min Range: -8.2248
Max Act: 8.2248. Min Act: -0.1700
Data Index: 6670486 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2248. Min Range: -8.2248
Max Act: 8.2248. Min Act: -0.1700
Data Index: 4599036 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2248. Min Range: -8.2248
Max Act: 8.1623. Min Act: -0.1700
Data Index: 7171444 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2248. Min Range: -8.2248
Max Act: 8.0685. Min Act: -0.1700
Data Index: 5747220 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2248. Min Range: -8.2248
Max Act: 8.0373. Min Act: -0.1700
Data Index: 566978 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.9748. Min Act: -0.1700
Data Index: 3601366 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.7873. Min Act: -0.1700
Data Index: 8220488 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.7560. Min Act: -0.1700
Data Index: 4414723 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.7560. Min Act: -0.1700
Data Index: 3723025 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.7248. Min Act: -0.1700
Data Index: 6672625 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.7248. Min Act: -0.1700
Data Index: 4958546 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.7248. Min Act: -0.1700
Data Index: 6007936 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.7248. Min Act: -0.1700
Data Index: 8027271 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.6935. Min Act: -0.1700
Data Index: 5069084 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.6623. Min Act: -0.1700
Data Index: 4955971 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.6623. Min Act: -0.1700
Data Index: 8713026 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.6623. Min Act: -0.1700
Data Index: 969075 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.6310. Min Act: -0.1700
Data Index: 6838200 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.5998. Min Act: -0.1700
Data Index: 6069752 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2248. Min Range: -8.2248
Max Act: 7.6310. Min Act: -0.1700
Data Index: 653303 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19