Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.7508. Min Act: -0.1700
Data Index: 4061007 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.7196. Min Act: -0.1700
Data Index: 7257802 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.6883. Min Act: -0.1700
Data Index: 2206726 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.5946. Min Act: -0.1700
Data Index: 4391613 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.5633. Min Act: -0.1700
Data Index: 2652501 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.5633. Min Act: -0.1700
Data Index: 5316415 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.5321. Min Act: -0.1700
Data Index: 6135308 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.5008. Min Act: -0.1700
Data Index: 1822368 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4696. Min Act: -0.1700
Data Index: 4160791 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4696. Min Act: -0.1700
Data Index: 4461675 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4696. Min Act: -0.1700
Data Index: 972832 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4383. Min Act: -0.1700
Data Index: 4939006 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4383. Min Act: -0.1700
Data Index: 971447 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4383. Min Act: -0.1700
Data Index: 7941272 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4071. Min Act: -0.1700
Data Index: 2021483 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.3758. Min Act: -0.1700
Data Index: 1268449 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.4071. Min Act: -0.1700
Data Index: 8574664 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.3758. Min Act: -0.1700
Data Index: 471139 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.3758. Min Act: -0.1700
Data Index: 6853659 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7508. Min Range: -4.7508
Max Act: 4.3758. Min Act: -0.1700
Data Index: 4005063 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19