Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5453 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3197. Min Range: -7.3197
Max Act: 7.3197. Min Act: -0.1700
Data Index: 2880251 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3197. Min Range: -7.3197
Max Act: 7.0072. Min Act: -0.1700
Data Index: 2548541 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.8197. Min Act: -0.1700
Data Index: 7270845 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.7260. Min Act: -0.1700
Data Index: 47486 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.7572. Min Act: -0.1700
Data Index: 1490748 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.6635. Min Act: -0.1700
Data Index: 7537643 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.6947. Min Act: -0.1700
Data Index: 6275779 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.6635. Min Act: -0.1700
Data Index: 1490751 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.6322. Min Act: -0.1700
Data Index: 8598570 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.6010. Min Act: -0.1700
Data Index: 408763 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5697. Min Act: -0.1700
Data Index: 2915616 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5697. Min Act: -0.1700
Data Index: 1490754 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5072. Min Act: -0.1700
Data Index: 3364991 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5072. Min Act: -0.1700
Data Index: 2638736 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5072. Min Act: -0.1700
Data Index: 8723231 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5072. Min Act: -0.1700
Data Index: 6565520 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5072. Min Act: -0.1700
Data Index: 7039599 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.4760. Min Act: -0.1700
Data Index: 5449557 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.5072. Min Act: -0.1700
Data Index: 1303624 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3197. Min Range: -7.3197
Max Act: 6.4447. Min Act: -0.1700
Data Index: 4994861 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19