Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1679 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4282. Min Range: -12.4282
Max Act: 12.4282. Min Act: -0.1700
Data Index: 3330533 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4282. Min Range: -12.4282
Max Act: 12.0532. Min Act: -0.1700
Data Index: 4115780 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.8657. Min Act: -0.1700
Data Index: 5014327 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.8657. Min Act: -0.1700
Data Index: 6439655 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.6782. Min Act: -0.1700
Data Index: 2916988 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.7407. Min Act: -0.1700
Data Index: 1378933 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.6782. Min Act: -0.1700
Data Index: 6769484 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.6157. Min Act: -0.1700
Data Index: 2530406 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.5532. Min Act: -0.1700
Data Index: 2516925 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.5532. Min Act: -0.1700
Data Index: 4663779 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.4907. Min Act: -0.1700
Data Index: 6841164 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.4907. Min Act: -0.1700
Data Index: 8461693 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.4907. Min Act: -0.1700
Data Index: 7896625 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.3032. Min Act: -0.1700
Data Index: 3632586 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.3032. Min Act: -0.1700
Data Index: 3146227 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.3032. Min Act: -0.1700
Data Index: 5955286 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.3032. Min Act: -0.1700
Data Index: 4751670 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.3032. Min Act: -0.1700
Data Index: 2278850 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.2407. Min Act: -0.1700
Data Index: 6883899 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4282. Min Range: -12.4282
Max Act: 11.2407. Min Act: -0.1700
Data Index: 7535814 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19