Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0598. Min Range: -8.0598
Max Act: 8.0598. Min Act: -0.1700
Data Index: 5889639 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.8411. Min Act: -0.1700
Data Index: 5683135 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.4973. Min Act: -0.1700
Data Index: 4264358 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.1848. Min Act: -0.1700
Data Index: 7334891 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.1848. Min Act: -0.1700
Data Index: 1220563 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.1536. Min Act: -0.1700
Data Index: 7547219 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.0911. Min Act: -0.1700
Data Index: 2116307 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.0911. Min Act: -0.1700
Data Index: 1599208 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.0598. Min Act: -0.1700
Data Index: 8666515 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.0598. Min Act: -0.1700
Data Index: 13850 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9973. Min Act: -0.1700
Data Index: 735488 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.0286. Min Act: -0.1700
Data Index: 5190146 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0598. Min Range: -8.0598
Max Act: 7.0286. Min Act: -0.1700
Data Index: 4573959 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9973. Min Act: -0.1700
Data Index: 5358815 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9661. Min Act: -0.1700
Data Index: 7353690 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9661. Min Act: -0.1700
Data Index: 5748506 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9661. Min Act: -0.1700
Data Index: 30763 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9661. Min Act: -0.1700
Data Index: 7733304 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9661. Min Act: -0.1700
Data Index: 5318623 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0598. Min Range: -8.0598
Max Act: 6.9348. Min Act: -0.1700
Data Index: 4563046 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19