Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5320 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1803. Min Range: -5.1803
Max Act: 5.1803. Min Act: -0.1700
Data Index: 95191 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.8365. Min Act: -0.1700
Data Index: 1088714 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.7428. Min Act: -0.1700
Data Index: 5397586 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.6490. Min Act: -0.1700
Data Index: 5231602 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.6490. Min Act: -0.1700
Data Index: 2845881 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.5865. Min Act: -0.1700
Data Index: 499797 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.5553. Min Act: -0.1700
Data Index: 2371401 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.5240. Min Act: -0.1700
Data Index: 6351820 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4928. Min Act: -0.1700
Data Index: 4419299 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4928. Min Act: -0.1700
Data Index: 1538496 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4928. Min Act: -0.1700
Data Index: 2371396 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4928. Min Act: -0.1700
Data Index: 6427415 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4928. Min Act: -0.1700
Data Index: 8181630 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4928. Min Act: -0.1700
Data Index: 8398606 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4303. Min Act: -0.1700
Data Index: 5294977 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4615. Min Act: -0.1700
Data Index: 615393 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4303. Min Act: -0.1700
Data Index: 6693942 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4615. Min Act: -0.1700
Data Index: 4284314 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4303. Min Act: -0.1700
Data Index: 4800578 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1803. Min Range: -5.1803
Max Act: 4.4303. Min Act: -0.1700
Data Index: 6013181 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19