Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1775 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.7497. Min Act: -0.1700
Data Index: 7123610 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.6247. Min Act: -0.1700
Data Index: 8768525 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.6247. Min Act: -0.1700
Data Index: 4926554 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5935. Min Act: -0.1700
Data Index: 3339262 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5935. Min Act: -0.1700
Data Index: 7907038 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5622. Min Act: -0.1700
Data Index: 1750709 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5622. Min Act: -0.1700
Data Index: 4287141 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5622. Min Act: -0.1700
Data Index: 4107434 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5622. Min Act: -0.1700
Data Index: 7718369 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5310. Min Act: -0.1700
Data Index: 4287339 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.5310. Min Act: -0.1700
Data Index: 409143 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4997. Min Act: -0.1700
Data Index: 4497107 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4997. Min Act: -0.1700
Data Index: 1893960 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4997. Min Act: -0.1700
Data Index: 1382115 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4997. Min Act: -0.1700
Data Index: 2069290 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4997. Min Act: -0.1700
Data Index: 7812134 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4997. Min Act: -0.1700
Data Index: 681312 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4997. Min Act: -0.1700
Data Index: 6411486 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4685. Min Act: -0.1700
Data Index: 6473728 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7497. Min Range: -6.7497
Max Act: 6.4685. Min Act: -0.1700
Data Index: 1275202 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19