Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4955 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1378. Min Range: -6.1378
Max Act: 6.1378. Min Act: -0.1700
Data Index: 5261197 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1378. Min Range: -6.1378
Max Act: 6.0753. Min Act: -0.1700
Data Index: 4853793 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1378. Min Range: -6.1378
Max Act: 6.0440. Min Act: -0.1700
Data Index: 7739299 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.9503. Min Act: -0.1700
Data Index: 6098415 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.8878. Min Act: -0.1700
Data Index: 6552794 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.8253. Min Act: -0.1700
Data Index: 4800582 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.8253. Min Act: -0.1700
Data Index: 4428646 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.7940. Min Act: -0.1700
Data Index: 2282498 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.7940. Min Act: -0.1700
Data Index: 217157 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.7315. Min Act: -0.1700
Data Index: 8261840 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.7003. Min Act: -0.1700
Data Index: 2498607 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.7003. Min Act: -0.1700
Data Index: 6917630 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.6690. Min Act: -0.1700
Data Index: 8712008 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.7003. Min Act: -0.1700
Data Index: 7401351 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.6690. Min Act: -0.1700
Data Index: 7486024 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.6690. Min Act: -0.1700
Data Index: 5443278 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.6690. Min Act: -0.1700
Data Index: 1792404 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.6690. Min Act: -0.1700
Data Index: 8690776 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.6378. Min Act: -0.1700
Data Index: 5101839 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1378. Min Range: -6.1378
Max Act: 5.6378. Min Act: -0.1700
Data Index: 458374 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19