Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5384 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.7014. Min Act: -0.1700
Data Index: 1015839 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.7014. Min Act: -0.1700
Data Index: 6986044 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.6076. Min Act: -0.1700
Data Index: 8667872 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.5451. Min Act: -0.1700
Data Index: 6333473 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.5139. Min Act: -0.1700
Data Index: 1897383 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.4514. Min Act: -0.1700
Data Index: 1150912 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.4826. Min Act: -0.1700
Data Index: 6253947 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.3576. Min Act: -0.1700
Data Index: 6374583 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.3263. Min Act: -0.1700
Data Index: 5580915 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.2951. Min Act: -0.1700
Data Index: 8067481 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.2951. Min Act: -0.1700
Data Index: 1933564 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.2638. Min Act: -0.1700
Data Index: 498878 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.2638. Min Act: -0.1700
Data Index: 1933563 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.2326. Min Act: -0.1700
Data Index: 2957767 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.2013. Min Act: -0.1700
Data Index: 3270414 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.2013. Min Act: -0.1700
Data Index: 876235 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.1388. Min Act: -0.1700
Data Index: 2712569 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.1388. Min Act: -0.1700
Data Index: 5093466 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.1388. Min Act: -0.1700
Data Index: 7166284 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7014. Min Range: -4.7014
Max Act: 4.1076. Min Act: -0.1700
Data Index: 8510266 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19