Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1700 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.6840. Min Act: -0.1700
Data Index: 6865741 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.4965. Min Act: -0.1700
Data Index: 7578539 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.4340. Min Act: -0.1700
Data Index: 2309877 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.3715. Min Act: -0.1700
Data Index: 5960110 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.3402. Min Act: -0.1700
Data Index: 784175 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.2465. Min Act: -0.1700
Data Index: 7749187 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.2152. Min Act: -0.1700
Data Index: 6046089 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.2152. Min Act: -0.1700
Data Index: 5226635 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.1840. Min Act: -0.1700
Data Index: 745373 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.1840. Min Act: -0.1700
Data Index: 3615795 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.1527. Min Act: -0.1700
Data Index: 7527487 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.1527. Min Act: -0.1700
Data Index: 2947104 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.1215. Min Act: -0.1700
Data Index: 8190032 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.1215. Min Act: -0.1700
Data Index: 3539429 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.0902. Min Act: -0.1700
Data Index: 7116326 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.0590. Min Act: -0.1700
Data Index: 3753563 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.0590. Min Act: -0.1700
Data Index: 7293927 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.0277. Min Act: -0.1700
Data Index: 1495416 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.0277. Min Act: -0.1700
Data Index: 2940079 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6840. Min Range: -5.6840
Max Act: 5.0277. Min Act: -0.1700
Data Index: 447454 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19