Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4103 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.8433. Min Act: -0.1700
Data Index: 2301743 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.6870. Min Act: -0.1700
Data Index: 5762377 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.7183. Min Act: -0.1700
Data Index: 1519881 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.6245. Min Act: -0.1700
Data Index: 351582 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.5620. Min Act: -0.1700
Data Index: 7479840 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.5620. Min Act: -0.1700
Data Index: 6662592 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.5308. Min Act: -0.1700
Data Index: 672744 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.4995. Min Act: -0.1700
Data Index: 3563921 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.4683. Min Act: -0.1700
Data Index: 2803029 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.4370. Min Act: -0.1700
Data Index: 2022816 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.4370. Min Act: -0.1700
Data Index: 5112085 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3745. Min Act: -0.1700
Data Index: 6658758 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3745. Min Act: -0.1700
Data Index: 4697610 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3120. Min Act: -0.1700
Data Index: 5085924 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3120. Min Act: -0.1700
Data Index: 5182263 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3120. Min Act: -0.1700
Data Index: 7048311 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3120. Min Act: -0.1700
Data Index: 880758 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3120. Min Act: -0.1700
Data Index: 1592450 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3120. Min Act: -0.1700
Data Index: 6434645 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8433. Min Range: -5.8433
Max Act: 5.3120. Min Act: -0.1700
Data Index: 2501400 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19