Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4727 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.5246. Min Act: -0.1700
Data Index: 5181013 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.3371. Min Act: -0.1700
Data Index: 1533650 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.3683. Min Act: -0.1700
Data Index: 2736232 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.3371. Min Act: -0.1700
Data Index: 2783529 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.3058. Min Act: -0.1700
Data Index: 3847491 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2745. Min Act: -0.1700
Data Index: 15840 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2745. Min Act: -0.1700
Data Index: 277614 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2745. Min Act: -0.1700
Data Index: 5093571 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2745. Min Act: -0.1700
Data Index: 1362279 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2745. Min Act: -0.1700
Data Index: 2626324 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2120. Min Act: -0.1700
Data Index: 4740627 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2433. Min Act: -0.1700
Data Index: 2661608 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2120. Min Act: -0.1700
Data Index: 1094560 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2433. Min Act: -0.1700
Data Index: 8827415 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2120. Min Act: -0.1700
Data Index: 4842363 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.1808. Min Act: -0.1700
Data Index: 6132410 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.1808. Min Act: -0.1700
Data Index: 1445548 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.1808. Min Act: -0.1700
Data Index: 1855420 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.1495. Min Act: -0.1700
Data Index: 906670 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5246. Min Range: -4.5246
Max Act: 4.2120. Min Act: -0.1700
Data Index: 606446 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19