Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.8569. Min Act: -0.1700
Data Index: 4312591 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.6382. Min Act: -0.1700
Data Index: 6134431 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.6069. Min Act: -0.1700
Data Index: 6245344 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.4507. Min Act: -0.1699
Data Index: 7183347 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.3569. Min Act: -0.1700
Data Index: 3211358 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.3569. Min Act: -0.1700
Data Index: 6365109 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.3257. Min Act: -0.1700
Data Index: 307737 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.2944. Min Act: -0.1700
Data Index: 3359161 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.2632. Min Act: -0.1700
Data Index: 7183329 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.2319. Min Act: -0.1700
Data Index: 7183337 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.2007. Min Act: -0.1700
Data Index: 1708264 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.1382. Min Act: -0.1700
Data Index: 3667198 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.1382. Min Act: -0.1700
Data Index: 7183339 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.1069. Min Act: -0.1700
Data Index: 3667197 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.1069. Min Act: -0.1700
Data Index: 7262232 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.1069. Min Act: -0.1700
Data Index: 4612711 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.0757. Min Act: -0.1700
Data Index: 1988721 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.0757. Min Act: -0.1700
Data Index: 7771629 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.0757. Min Act: -0.1700
Data Index: 4028283 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8569. Min Range: -5.8569
Max Act: 5.0757. Min Act: -0.1700
Data Index: 630424 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19