Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3937. Min Act: -0.1700
Data Index: 1422629 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3625. Min Act: -0.1700
Data Index: 1422628 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3625. Min Act: -0.1700
Data Index: 4315794 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3312. Min Act: -0.1700
Data Index: 4967825 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3312. Min Act: -0.1700
Data Index: 1422630 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.3312. Min Act: -0.1700
Data Index: 2736410 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2687. Min Act: -0.1700
Data Index: 993922 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2375. Min Act: -0.1700
Data Index: 5197848 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2375. Min Act: -0.1700
Data Index: 3521624 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2375. Min Act: -0.1700
Data Index: 1422625 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2062. Min Act: -0.1700
Data Index: 1136971 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2062. Min Act: -0.1700
Data Index: 6815482 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2062. Min Act: -0.1700
Data Index: 7346958 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.2375. Min Act: -0.1700
Data Index: 7346959 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1750. Min Act: -0.1700
Data Index: 8385526 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1750. Min Act: -0.1700
Data Index: 2319481 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1750. Min Act: -0.1700
Data Index: 4328764 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1750. Min Act: -0.1700
Data Index: 7346954 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1750. Min Act: -0.1700
Data Index: 2736409 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3937. Min Range: -6.3937
Max Act: 6.1437. Min Act: -0.1700
Data Index: 5674638 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19