Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2404 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.6916. Min Act: -0.1700
Data Index: 1351241 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.3166. Min Act: -0.1700
Data Index: 5086354 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.3166. Min Act: -0.1700
Data Index: 1205952 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.3791. Min Act: -0.1700
Data Index: 1496365 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.2541. Min Act: -0.1700
Data Index: 5375764 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.2541. Min Act: -0.1700
Data Index: 5662342 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.0978. Min Act: -0.1700
Data Index: 8726667 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6916. Min Range: -8.6916
Max Act: 8.0353. Min Act: -0.1700
Data Index: 7942582 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.9416. Min Act: -0.1700
Data Index: 2285565 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.9103. Min Act: -0.1700
Data Index: 3566383 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.8791. Min Act: -0.1700
Data Index: 6906727 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.8478. Min Act: -0.1700
Data Index: 5862408 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.8478. Min Act: -0.1700
Data Index: 1178579 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.8478. Min Act: -0.1700
Data Index: 1160320 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.7853. Min Act: -0.1700
Data Index: 8203705 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.7541. Min Act: -0.1700
Data Index: 2901544 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.7541. Min Act: -0.1700
Data Index: 1444597 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.6603. Min Act: -0.1700
Data Index: 1758748 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.6291. Min Act: -0.1700
Data Index: 6447583 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6916. Min Range: -8.6916
Max Act: 7.5978. Min Act: -0.1700
Data Index: 2056902 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19