Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5220 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5607. Min Range: -8.5607
Max Act: 8.5607. Min Act: -0.1700
Data Index: 3885260 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5607. Min Range: -8.5607
Max Act: 8.4357. Min Act: -0.1700
Data Index: 1603313 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5607. Min Range: -8.5607
Max Act: 8.1232. Min Act: -0.1700
Data Index: 4403118 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5607. Min Range: -8.5607
Max Act: 8.1232. Min Act: -0.1700
Data Index: 5894959 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5607. Min Range: -8.5607
Max Act: 8.0607. Min Act: -0.1700
Data Index: 7372257 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.9982. Min Act: -0.1700
Data Index: 2514718 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.9982. Min Act: -0.1700
Data Index: 6909078 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.9670. Min Act: -0.1700
Data Index: 8692221 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.9357. Min Act: -0.1700
Data Index: 6862803 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.9045. Min Act: -0.1700
Data Index: 7843821 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.8732. Min Act: -0.1700
Data Index: 7842018 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.8420. Min Act: -0.1700
Data Index: 3284415 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.8107. Min Act: -0.1700
Data Index: 7291226 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.8107. Min Act: -0.1700
Data Index: 2651976 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.7795. Min Act: -0.1700
Data Index: 7859762 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.7795. Min Act: -0.1700
Data Index: 7021494 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.7482. Min Act: -0.1700
Data Index: 4317277 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.7795. Min Act: -0.1700
Data Index: 5580324 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.7482. Min Act: -0.1700
Data Index: 7682262 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5607. Min Range: -8.5607
Max Act: 7.7482. Min Act: -0.1700
Data Index: 4237776 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19