Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1815. Min Range: -7.1815
Max Act: 7.1815. Min Act: -0.1700
Data Index: 5473176 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1815. Min Range: -7.1815
Max Act: 7.1815. Min Act: -0.1700
Data Index: 6441729 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.8690. Min Act: -0.1700
Data Index: 6591000 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.8690. Min Act: -0.1700
Data Index: 4152860 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.8690. Min Act: -0.1700
Data Index: 6965621 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.7440. Min Act: -0.1700
Data Index: 5553499 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.6815. Min Act: -0.1700
Data Index: 7833883 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.6815. Min Act: -0.1700
Data Index: 8088622 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.6815. Min Act: -0.1700
Data Index: 3812219 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.6503. Min Act: -0.1700
Data Index: 8128247 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.6190. Min Act: -0.1700
Data Index: 5839071 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.5878. Min Act: -0.1700
Data Index: 4301730 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.5253. Min Act: -0.1700
Data Index: 662568 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.5253. Min Act: -0.1700
Data Index: 1141692 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.5878. Min Act: -0.1700
Data Index: 3603811 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.4940. Min Act: -0.1700
Data Index: 1703761 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.5253. Min Act: -0.1700
Data Index: 2156735 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.4628. Min Act: -0.1700
Data Index: 185549 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.4628. Min Act: -0.1700
Data Index: 2279139 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1815. Min Range: -7.1815
Max Act: 6.4940. Min Act: -0.1700
Data Index: 1770485 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19