Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.8405. Min Act: -0.1700
Data Index: 5596194 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.7468. Min Act: -0.1700
Data Index: 6667341 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.6530. Min Act: -0.1700
Data Index: 512738 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.6218. Min Act: -0.1700
Data Index: 7602855 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.5905. Min Act: -0.1700
Data Index: 4760664 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.6218. Min Act: -0.1700
Data Index: 5483202 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.5905. Min Act: -0.1700
Data Index: 2336437 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.5593. Min Act: -0.1700
Data Index: 8088483 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.5905. Min Act: -0.1700
Data Index: 5777849 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.5593. Min Act: -0.1700
Data Index: 6992134 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.5593. Min Act: -0.1700
Data Index: 88916 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.5280. Min Act: -0.1700
Data Index: 6671028 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 2627726 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 3073162 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 3278874 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 4320629 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 7688831 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 7774644 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 5901420 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8405. Min Range: -6.8405
Max Act: 6.4968. Min Act: -0.1700
Data Index: 4310283 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19