Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.3204. Min Act: -0.1700
Data Index: 3703612 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.2579. Min Act: -0.1700
Data Index: 1438862 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.2266. Min Act: -0.1700
Data Index: 7113434 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.1641. Min Act: -0.1700
Data Index: 946264 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.1329. Min Act: -0.1700
Data Index: 2390608 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.1329. Min Act: -0.1700
Data Index: 3061546 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.0704. Min Act: -0.1700
Data Index: 1105460 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.1016. Min Act: -0.1700
Data Index: 6885927 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.1016. Min Act: -0.1700
Data Index: 7488054 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.1016. Min Act: -0.1700
Data Index: 3037778 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.0704. Min Act: -0.1700
Data Index: 8351578 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.0704. Min Act: -0.1700
Data Index: 7941371 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.0391. Min Act: -0.1700
Data Index: 7577069 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3204. Min Range: -4.3204
Max Act: 4.0391. Min Act: -0.1700
Data Index: 5589947 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3204. Min Range: -4.3204
Max Act: 3.9766. Min Act: -0.1700
Data Index: 7564205 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3204. Min Range: -4.3204
Max Act: 3.9141. Min Act: -0.1700
Data Index: 3851525 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3204. Min Range: -4.3204
Max Act: 3.9453. Min Act: -0.1700
Data Index: 6965998 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3204. Min Range: -4.3204
Max Act: 3.9453. Min Act: -0.1700
Data Index: 6927012 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3204. Min Range: -4.3204
Max Act: 3.9766. Min Act: -0.1700
Data Index: 1031273 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3204. Min Range: -4.3204
Max Act: 3.9453. Min Act: -0.1700
Data Index: 4576546 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19