Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0306. Min Range: -6.0306
Max Act: 6.0306. Min Act: -0.1700
Data Index: 1135213 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.9993. Min Act: -0.1700
Data Index: 5290480 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.9368. Min Act: -0.1700
Data Index: 1151575 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.7806. Min Act: -0.1700
Data Index: 740328 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.6868. Min Act: -0.1700
Data Index: 198500 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.6556. Min Act: -0.1700
Data Index: 5439554 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.5618. Min Act: -0.1700
Data Index: 1072507 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.5618. Min Act: -0.1700
Data Index: 2296288 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.5618. Min Act: -0.1700
Data Index: 5456821 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.4681. Min Act: -0.1700
Data Index: 4541200 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.4681. Min Act: -0.1700
Data Index: 7212061 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.3743. Min Act: -0.1700
Data Index: 1962528 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.4056. Min Act: -0.1700
Data Index: 8205552 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.4056. Min Act: -0.1700
Data Index: 4926698 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.4368. Min Act: -0.1700
Data Index: 4628580 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.3431. Min Act: -0.1700
Data Index: 6111328 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.3743. Min Act: -0.1700
Data Index: 883918 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.3743. Min Act: -0.1700
Data Index: 2138398 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.3743. Min Act: -0.1700
Data Index: 8628866 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0306. Min Range: -6.0306
Max Act: 5.3743. Min Act: -0.1700
Data Index: 381801 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19