Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.8488. Min Range: -15.8488
Max Act: 15.8488. Min Act: -0.1700
Data Index: 3691612 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.8488. Min Range: -15.8488
Max Act: 15.2863. Min Act: -0.1700
Data Index: 490126 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.8488. Min Range: -15.8488
Max Act: 15.2238. Min Act: -0.1700
Data Index: 3719889 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.8488. Min Range: -15.8488
Max Act: 15.0988. Min Act: -0.1700
Data Index: 7916395 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.8488. Min Range: -15.8488
Max Act: 15.0363. Min Act: -0.1700
Data Index: 4586441 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.8488. Min Range: -15.8488
Max Act: 15.0363. Min Act: -0.1700
Data Index: 4939895 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9738. Min Act: -0.1700
Data Index: 3340540 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9738. Min Act: -0.1700
Data Index: 395604 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9738. Min Act: -0.1700
Data Index: 6615839 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9738. Min Act: -0.1700
Data Index: 3789619 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9738. Min Act: -0.1700
Data Index: 6120445 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9738. Min Act: -0.1700
Data Index: 5558920 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9738. Min Act: -0.1700
Data Index: 2995528 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.8488. Min Act: -0.1700
Data Index: 2552218 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.9113. Min Act: -0.1700
Data Index: 5415522 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.8488. Min Act: -0.1700
Data Index: 5637058 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.7863. Min Act: -0.1700
Data Index: 8756231 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.7238. Min Act: -0.1700
Data Index: 6288644 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.7238. Min Act: -0.1700
Data Index: 467722 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.8488. Min Range: -15.8488
Max Act: 14.7238. Min Act: -0.1700
Data Index: 5078842 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19