Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4531 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2420. Min Range: -8.2420
Max Act: 8.2420. Min Act: -0.1700
Data Index: 928835 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2420. Min Range: -8.2420
Max Act: 8.1795. Min Act: -0.1700
Data Index: 37685 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.9920. Min Act: -0.1700
Data Index: 6893005 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.9920. Min Act: -0.1700
Data Index: 1050683 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.9295. Min Act: -0.1700
Data Index: 5441602 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.9295. Min Act: -0.1700
Data Index: 6945847 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.8670. Min Act: -0.1700
Data Index: 6252686 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.8045. Min Act: -0.1700
Data Index: 1752196 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.8670. Min Act: -0.1700
Data Index: 2675543 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.8045. Min Act: -0.1700
Data Index: 218318 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.7420. Min Act: -0.1700
Data Index: 8634106 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.7420. Min Act: -0.1700
Data Index: 4255342 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.8045. Min Act: -0.1700
Data Index: 2753092 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.7420. Min Act: -0.1700
Data Index: 944998 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.6795. Min Act: -0.1700
Data Index: 109013 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.6795. Min Act: -0.1700
Data Index: 5562839 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.6795. Min Act: -0.1700
Data Index: 4182124 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.6795. Min Act: -0.1700
Data Index: 6654952 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.6170. Min Act: -0.1700
Data Index: 6878640 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2420. Min Range: -8.2420
Max Act: 7.6170. Min Act: -0.1700
Data Index: 4151522 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19