Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.5769. Min Act: -0.1700
Data Index: 2295521 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.5455. Min Act: -0.1700
Data Index: 78637 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4516. Min Act: -0.1700
Data Index: 5323751 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4516. Min Act: -0.1700
Data Index: 7030163 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4516. Min Act: -0.1700
Data Index: 4809690 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4359. Min Act: -0.1700
Data Index: 104253 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4202. Min Act: -0.1700
Data Index: 8211760 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4359. Min Act: -0.1700
Data Index: 4937393 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4045. Min Act: -0.1700
Data Index: 2413237 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.4202. Min Act: -0.1700
Data Index: 1775527 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3732. Min Act: -0.1700
Data Index: 3926394 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3732. Min Act: -0.1700
Data Index: 3430977 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3732. Min Act: -0.1700
Data Index: 531481 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3732. Min Act: -0.1700
Data Index: 8034031 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3575. Min Act: -0.1700
Data Index: 8692745 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3575. Min Act: -0.1700
Data Index: 7124190 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3575. Min Act: -0.1700
Data Index: 7883621 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3575. Min Act: -0.1700
Data Index: 5769893 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3575. Min Act: -0.1700
Data Index: 3051426 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5769. Min Range: -3.5769
Max Act: 3.3418. Min Act: -0.1700
Data Index: 5348531 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19