Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 359 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0799. Min Range: -6.0799
Max Act: 6.0799. Min Act: -0.1700
Data Index: 1856629 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0799. Min Range: -6.0799
Max Act: 6.0799. Min Act: -0.1700
Data Index: 6107956 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0799. Min Range: -6.0799
Max Act: 6.0799. Min Act: -0.1700
Data Index: 2393487 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0799. Min Range: -6.0799
Max Act: 6.0486. Min Act: -0.1700
Data Index: 3035804 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.9861. Min Act: -0.1700
Data Index: 8255710 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0799. Min Range: -6.0799
Max Act: 6.0174. Min Act: -0.1700
Data Index: 4030106 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.9861. Min Act: -0.1700
Data Index: 6197590 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.9861. Min Act: -0.1700
Data Index: 2358271 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.9236. Min Act: -0.1700
Data Index: 2727996 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.9236. Min Act: -0.1700
Data Index: 8497334 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.9236. Min Act: -0.1700
Data Index: 6952210 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.9236. Min Act: -0.1700
Data Index: 4615234 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.8924. Min Act: -0.1700
Data Index: 5074272 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.8611. Min Act: -0.1700
Data Index: 3750734 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.8299. Min Act: -0.1700
Data Index: 8198955 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.7986. Min Act: -0.1700
Data Index: 7549131 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.7986. Min Act: -0.1700
Data Index: 1519315 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.7674. Min Act: -0.1700
Data Index: 7827077 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.7674. Min Act: -0.1700
Data Index: 3328648 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0799. Min Range: -6.0799
Max Act: 5.7674. Min Act: -0.1700
Data Index: 3982034 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19