Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1562 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.5705. Min Act: -0.1700
Data Index: 7570207 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.4455. Min Act: -0.1700
Data Index: 3310811 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.3830. Min Act: -0.1700
Data Index: 2208827 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.3205. Min Act: -0.1700
Data Index: 658539 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.2892. Min Act: -0.1700
Data Index: 4381822 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.2580. Min Act: -0.1700
Data Index: 4569276 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.2580. Min Act: -0.1700
Data Index: 490482 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.2267. Min Act: -0.1700
Data Index: 2633473 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.2267. Min Act: -0.1700
Data Index: 1814368 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1955. Min Act: -0.1700
Data Index: 5516142 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1955. Min Act: -0.1700
Data Index: 3269685 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1642. Min Act: -0.1700
Data Index: 8641258 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1955. Min Act: -0.1700
Data Index: 8641263 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1642. Min Act: -0.1700
Data Index: 6856054 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1642. Min Act: -0.1700
Data Index: 8039378 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1642. Min Act: -0.1700
Data Index: 6671879 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1330. Min Act: -0.1700
Data Index: 1928257 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1330. Min Act: -0.1700
Data Index: 7911741 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1017. Min Act: -0.1700
Data Index: 1276454 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5705. Min Range: -4.5705
Max Act: 4.1017. Min Act: -0.1700
Data Index: 2875330 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19