Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4433 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.9497. Min Act: -0.1700
Data Index: 8023165 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.4185. Min Act: -0.1700
Data Index: 4377401 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.3560. Min Act: -0.1700
Data Index: 7477083 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.3247. Min Act: -0.1700
Data Index: 1118793 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.2935. Min Act: -0.1700
Data Index: 3092186 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.2935. Min Act: -0.1700
Data Index: 6591244 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.1685. Min Act: -0.1700
Data Index: 6937422 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.1372. Min Act: -0.1700
Data Index: 6339610 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.1372. Min Act: -0.1700
Data Index: 6753748 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.1372. Min Act: -0.1700
Data Index: 4497501 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.1060. Min Act: -0.1700
Data Index: 6372162 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.1060. Min Act: -0.1700
Data Index: 2709895 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.0747. Min Act: -0.1700
Data Index: 1366672 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.0747. Min Act: -0.1700
Data Index: 7896766 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9497. Min Range: -6.9497
Max Act: 6.0435. Min Act: -0.1700
Data Index: 286274 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9497. Min Range: -6.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 4752352 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9497. Min Range: -6.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 8103861 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9497. Min Range: -6.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 7407076 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9497. Min Range: -6.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 2122334 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9497. Min Range: -6.9497
Max Act: 5.9497. Min Act: -0.1700
Data Index: 1423645 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19