Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2880. Min Range: -8.2880
Max Act: 8.2880. Min Act: -0.1700
Data Index: 2250020 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.8818. Min Act: -0.1700
Data Index: 8624321 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.7568. Min Act: -0.1700
Data Index: 336703 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.7255. Min Act: -0.1700
Data Index: 5992211 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.6943. Min Act: -0.1700
Data Index: 1825351 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.6318. Min Act: -0.1700
Data Index: 7541919 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.6630. Min Act: -0.1700
Data Index: 5343481 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.6005. Min Act: -0.1700
Data Index: 4854266 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.5693. Min Act: -0.1700
Data Index: 5732068 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.5380. Min Act: -0.1700
Data Index: 5498539 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.5068. Min Act: -0.1700
Data Index: 3412685 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.5068. Min Act: -0.1700
Data Index: 6158554 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.4755. Min Act: -0.1700
Data Index: 6084983 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.4443. Min Act: -0.1700
Data Index: 881691 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.4130. Min Act: -0.1700
Data Index: 2107909 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.3818. Min Act: -0.1700
Data Index: 3084473 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.3818. Min Act: -0.1700
Data Index: 3359605 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.3818. Min Act: -0.1700
Data Index: 457817 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.3818. Min Act: -0.1700
Data Index: 8070166 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2880. Min Range: -8.2880
Max Act: 7.3505. Min Act: -0.1700
Data Index: 3166643 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19