Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1792 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.4781. Min Act: -0.1700
Data Index: 1599684 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.4469. Min Act: -0.1700
Data Index: 3730460 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.3844. Min Act: -0.1700
Data Index: 6257170 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.3219. Min Act: -0.1700
Data Index: 4224813 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.2281. Min Act: -0.1700
Data Index: 7836636 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1656. Min Act: -0.1700
Data Index: 4628103 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1656. Min Act: -0.1700
Data Index: 4067740 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1344. Min Act: -0.1700
Data Index: 8639104 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1344. Min Act: -0.1700
Data Index: 3826872 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1031. Min Act: -0.1700
Data Index: 2420320 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1031. Min Act: -0.1700
Data Index: 8604495 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0719. Min Act: -0.1700
Data Index: 3910620 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1344. Min Act: -0.1700
Data Index: 3577530 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1031. Min Act: -0.1700
Data Index: 719547 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1031. Min Act: -0.1700
Data Index: 4362576 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0406. Min Act: -0.1700
Data Index: 357790 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0406. Min Act: -0.1700
Data Index: 8010676 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0406. Min Act: -0.1700
Data Index: 5350522 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0406. Min Act: -0.1700
Data Index: 1569978 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0094. Min Act: -0.1700
Data Index: 5371719 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19