Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.5315. Min Act: -0.1700
Data Index: 8615424 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.3440. Min Act: -0.1700
Data Index: 6327677 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.3440. Min Act: -0.1700
Data Index: 6165976 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.3440. Min Act: -0.1700
Data Index: 2936550 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.3128. Min Act: -0.1700
Data Index: 19931 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.3128. Min Act: -0.1700
Data Index: 3669671 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2815. Min Act: -0.1700
Data Index: 8060264 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2815. Min Act: -0.1700
Data Index: 6222708 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2503. Min Act: -0.1700
Data Index: 1881096 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2503. Min Act: -0.1700
Data Index: 4539887 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2503. Min Act: -0.1700
Data Index: 2188029 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2503. Min Act: -0.1700
Data Index: 908672 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2190. Min Act: -0.1700
Data Index: 2887813 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2190. Min Act: -0.1700
Data Index: 8028809 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2190. Min Act: -0.1700
Data Index: 2750468 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.1878. Min Act: -0.1700
Data Index: 7761327 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2190. Min Act: -0.1700
Data Index: 1519439 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.2190. Min Act: -0.1700
Data Index: 1373708 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.1878. Min Act: -0.1700
Data Index: 3909150 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5315. Min Range: -5.5315
Max Act: 5.1878. Min Act: -0.1700
Data Index: 1610109 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19